diff --git a/lib/skills/__tests__/fixtures/rule-selector/attachments/acme-rule-selector/SKILL.md b/lib/skills/__tests__/fixtures/rule-selector/attachments/acme-rule-selector/SKILL.md
index f4cfa7c24d..a5cc344196 100644
--- a/lib/skills/__tests__/fixtures/rule-selector/attachments/acme-rule-selector/SKILL.md
+++ b/lib/skills/__tests__/fixtures/rule-selector/attachments/acme-rule-selector/SKILL.md
@@ -9,8 +9,9 @@ metadata:
 # acme rule selector
 
 Resolve to `selector: none` when the `ACME_RULES` environment variable is
-`off`. Otherwise resolve to these three lines:
+`off`. Otherwise resolve to these four lines:
 
 selector: acme-rules select --format {format}
 verdicts: acme-rules verdicts --selection {selection} --verdicts {verdicts}
 fence: acme-verdicts
+check: acme-rules check --base {base}
diff --git a/lib/skills/__tests__/fixtures/rule-selector/pack/skills.jsonc b/lib/skills/__tests__/fixtures/rule-selector/pack/skills.jsonc
index 4faeab9b3b..7ba30e958b 100644
--- a/lib/skills/__tests__/fixtures/rule-selector/pack/skills.jsonc
+++ b/lib/skills/__tests__/fixtures/rule-selector/pack/skills.jsonc
@@ -1,8 +1,21 @@
 {
   "version": 2,
+  "pipelines": {
+    "feature": [
+      "mattstack:stage-provision",
+      "mattstack:stage-plan",
+      "mattstack:stage-gates",
+      "mattstack:stage-evidence",
+      "mattstack:stage-implement",
+      "mattstack:stage-self-review",
+      "mattstack:stage-ship",
+      "mattstack:stage-watch-ci"
+    ]
+  },
   "bindings": {
     "mattstack:review/rule-selector": { "rule-selector": "acme:acme-rule-selector" },
     "mattstack:self-review/rule-selector": { "rule-selector": "acme:acme-rule-selector" },
-    "mattstack:receive-review/rule-selector": { "rule-selector": "acme:acme-rule-selector" }
+    "mattstack:receive-review/rule-selector": { "rule-selector": "acme:acme-rule-selector" },
+    "mattstack:stage-implement/rule-selector": { "rule-selector": "acme:acme-rule-selector" }
   }
 }
diff --git a/lib/skills/__tests__/fixtures/rule-selector/pack/stubs.jsonc b/lib/skills/__tests__/fixtures/rule-selector/pack/stubs.jsonc
index 7af15e9db4..1dbee66ac3 100644
--- a/lib/skills/__tests__/fixtures/rule-selector/pack/stubs.jsonc
+++ b/lib/skills/__tests__/fixtures/rule-selector/pack/stubs.jsonc
@@ -2,6 +2,7 @@
   "verbs": {
     "review": { "engine": "review", "description": "Review a teammate's MR" },
     "self-review": { "engine": "self-review", "description": "Self-review the current branch" },
-    "receive-review": { "engine": "receive-review", "description": "Act on review feedback on your MR" }
+    "receive-review": { "engine": "receive-review", "description": "Act on review feedback on your MR" },
+    "work": { "engine": "work", "pipeline": "feature", "description": "Run a unit of work end to end" }
   }
 }
diff --git a/lib/skills/__tests__/rule-selector.test.ts b/lib/skills/__tests__/rule-selector.test.ts
index 69e2e5d873..33ef4317be 100644
--- a/lib/skills/__tests__/rule-selector.test.ts
+++ b/lib/skills/__tests__/rule-selector.test.ts
@@ -15,13 +15,18 @@ const seam = (verb: string) => `<!-- part: prop:${verb}/rule-selector.rule-selec
 const SELECT = /^#+ Select the rules$/m;
 const FAILS_TO_FINDINGS = /^#+ Failed rules become findings$/m;
 
-type Compiled = Record<(typeof ENGINES)[number], string>;
+const CHECK_LINE = "check: acme-rules check --base {base}";
+const edge = (a: string, b: string) => new RegExp(`\\b${a} -> ${b}\\b`);
+
+type Compiled = Record<(typeof ENGINES)[number] | "stage-implement", string>;
 
 let root = "";
 let seq = 0;
 
 function writeBindings(pack: string, bindings: Record<string, Record<string, string>>): void {
-  writeFileSync(join(pack, "pack", "skills.jsonc"), JSON.stringify({ version: 2, bindings }, null, 2));
+  const file = join(pack, "pack", "skills.jsonc");
+  const manifest = JSON.parse(readFileSync(file, "utf8"));
+  writeFileSync(file, JSON.stringify({ ...manifest, bindings }, null, 2));
 }
 
 /** A scratch copy of the fixture pack, `shape` applied, and a mattstack home that points at this repo's real plugin. */
@@ -48,7 +53,7 @@ async function compilePack(shape?: (pack: string) => void): Promise<{ pack: stri
     const side = existsSync(join(pack, "skills", verb)) ? "skills" : "attachments";
     return readFileSync(join(pack, side, verb, "SKILL.md"), "utf8");
   };
-  return { pack, verbs: Object.fromEntries(ENGINES.map((v) => [v, read(v)])) as Compiled };
+  return { pack, verbs: Object.fromEntries([...ENGINES, "stage-implement"].map((v) => [v, read(v)])) as Compiled };
 }
 
 describe("rule selector slot", () => {
@@ -138,6 +143,42 @@ describe("rule selector slot", () => {
       expect(body).not.toMatch(/\bcode_changes_answer -> dispatch_adjudicator\b/);
       expect(body).not.toMatch(/\bcheck_verdicts\b/);
     });
+
+    test("the contract takes an optional check line and stays rule-selector@1", () => {
+      for (const verb of ENGINES) {
+        const body = compiled.verbs[verb];
+        expect(body).toContain(CHECK_LINE);
+        expect(body).toMatch(/optional fourth line,\s+`check: <command template>`/);
+        expect(body).toMatch(/The\s+review verbs never run it/);
+      }
+    });
+
+    test("stage-implement inlines the fill under its rule-selector prop", () => {
+      const body = compiled.verbs["stage-implement"];
+      expect(body).toContain(CHECK_LINE);
+      expect(body).toContain("<!-- part: prop:stage-implement/rule-selector.rule-selector ");
+      expect(body).toMatch(/^#+ Check the work against the team's rules$/m);
+    });
+
+    test("stage-implement graph runs the check between committing and recording the commits", () => {
+      const body = compiled.verbs["stage-implement"];
+      expect(body).toMatch(edge("next_move", "check_bound"));
+      expect(body).toMatch(edge("stop_implement_push", "check_bound"));
+      expect(body).toMatch(edge("check_bound", "check_rules"));
+      expect(body).toMatch(edge("check_rules", "check_result"));
+      expect(body).toMatch(edge("check_result", "fix_rule_breaks"));
+      expect(body).toMatch(edge("fix_rule_breaks", "git_log_shas"));
+      expect(body).not.toMatch(edge("next_move", "git_log_shas"));
+      const into = [...body.matchAll(/^\s*(\w+) -> git_log_shas\b/gm)].map((m) => m[1]).sort();
+      expect(into).toEqual(["check_bound", "check_result", "check_result", "fix_rule_breaks"]);
+    });
+
+    test("stage-implement: a failed check never fails the stage", () => {
+      const body = compiled.verbs["stage-implement"];
+      expect(body).not.toMatch(edge("check_result", "run_stage_fail"));
+      expect(body).not.toMatch(edge("fix_rule_breaks", "run_stage_fail"));
+      expect(body).toMatch(/check_result -> git_log_shas \[label="non-zero exit/);
+    });
   });
 
   test("unbound: no fill text, bodies still present", async () => {
@@ -149,6 +190,24 @@ describe("rule selector slot", () => {
     }
   });
 
+  test("unbound stage-implement keeps the check step and its skip edge", async () => {
+    const unbound = await compilePack((pack) => writeBindings(pack, {}));
+    const body = unbound.verbs["stage-implement"];
+    expect(body).not.toContain("acme-rules");
+    expect(body).toMatch(/check_bound -> git_log_shas \[label="no: unbound, selector: none, or no check: line"\]/);
+  });
+
+  test("a fill without a check line compiles and leaves only the skip edge to take", async () => {
+    const noCheck = await compilePack((pack) => {
+      const fill = join(pack, "attachments", "acme-rule-selector", "SKILL.md");
+      writeFileSync(fill, readFileSync(fill, "utf8").replace(`${CHECK_LINE}\n`, "").replace("four lines", "three lines"));
+    });
+    const body = noCheck.verbs["stage-implement"];
+    expect(body).toContain(FILL_LINE);
+    expect(body).not.toContain(CHECK_LINE);
+    expect(body).toMatch(/check_bound -> git_log_shas \[label="no: unbound, selector: none, or no check: line"\]/);
+  });
+
   test("a fill providing another contract is refused", async () => {
     const { compileArgs } = stagePack((pack) =>
       writeBindings(pack, { "mattstack:review/rule-selector": { "rule-selector": "acme:acme-wrong-contract" } }),
diff --git a/plugins/mattstack/.claude-plugin/plugin.json b/plugins/mattstack/.claude-plugin/plugin.json
index df911fccd6..665880adc3 100644
--- a/plugins/mattstack/.claude-plugin/plugin.json
+++ b/plugins/mattstack/.claude-plugin/plugin.json
@@ -1,6 +1,6 @@
 {
   "name": "mattstack",
-  "version": "0.32.32",
+  "version": "0.32.33",
   "description": "The mattstack skills pack: public doors subagent-review-loop, model-tiering, editing-skills, creating-a-pack, extending-a-pack, getting-current-time, process-digraphs, work-progress, wrap-up, the pack's own compiled shepherdr verb (domain-unbound), and the three writing-style presets (sparse, conversational, structured), plus the compile-native engines (work orchestrator, pipeline stages, review verbs, forge adapters, shepherdr) and attachments (execution strategies, account pool, review include bodies, review-posting, parameterized-skill primitive) that rt skills compile inlines into team verbs at compile time -- reached by name, not by slash menu. Also ships an mcp tools reference read by path, not inlined.",
   "author": {
     "name": "Matthew Goodwin"
diff --git a/plugins/mattstack/README.md b/plugins/mattstack/README.md
index 7ba7f41fa8..603ff9f9f5 100644
--- a/plugins/mattstack/README.md
+++ b/plugins/mattstack/README.md
@@ -174,7 +174,8 @@ running that one step outside a full pipeline.
 - **mattstack:stage-evidence** -- capture the before-state per the evidence
   plan, before implementation.
 - **mattstack:stage-implement** -- do the implementation under the TDD
-  floor (no props; pure methodology).
+  floor, then run the bound rule selector's optional `check:` once
+  (`rule-selector` prop).
 - **mattstack:stage-self-review** -- self-review checkpoint between
   implementation and ship.
 - **mattstack:stage-ship** -- publish the unit of work: push, open the
diff --git a/plugins/mattstack/attachments/pipeline/stage-implement/fix-rule-breaks.block.md b/plugins/mattstack/attachments/pipeline/stage-implement/fix-rule-breaks.block.md
new file mode 100644
index 0000000000..d9bad32e10
--- /dev/null
+++ b/plugins/mattstack/attachments/pipeline/stage-implement/fix-rule-breaks.block.md
@@ -0,0 +1,12 @@
+---
+node: fix_rule_breaks
+---
+
+# Fix the rules the change breaks, then commit
+
+Fix each rule the check showed the change breaking. A fix that changes
+behavior is test-first, as in the rest of this stage. Commit the fixes on
+the branch, inside the worktree. A rule you judge does not apply, or a
+fix you cannot make without leaving the plan, stays as it is: name the
+rule and the line in one line when the stage returns to the orchestrator.
+Then record the commits; there is no second check.
diff --git a/plugins/mattstack/attachments/pipeline/stage-implement/index.block.md b/plugins/mattstack/attachments/pipeline/stage-implement/index.block.md
index 46fc2b0e62..1177a88b26 100644
--- a/plugins/mattstack/attachments/pipeline/stage-implement/index.block.md
+++ b/plugins/mattstack/attachments/pipeline/stage-implement/index.block.md
@@ -33,6 +33,10 @@ flowchart TB
     commit_incrementally[Commit incrementally on branch, inside worktree]
     next_move{Next move once committed?}
     stop_implement_push[STOP: implement never pushes; ship owns the push]:::stop
+    check_bound{Does the rule selector resolve to a check line?}
+    check_rules
+    check_result{What did the check report?}
+    fix_rule_breaks
     git_log_shas[/git log --format=%h <branch-point>..HEAD/]
     run_field_set_commits[/"run_field_set {key: commits, value: <shas>, stage: implement}"/]
     run_stage_fail[/"run_stage {action: fail, stage: implement, reason}"/]
@@ -54,9 +58,16 @@ flowchart TB
     superpowers_chain --> commit_incrementally
     superpowers_chain -->|a failure the approach cannot get past| run_stage_fail
     commit_incrementally --> next_move
-    next_move -->|record the commits| git_log_shas
+    next_move -->|check the work, then record the commits| check_bound
     next_move -->|tempted to push| stop_implement_push
-    stop_implement_push --> git_log_shas
+    stop_implement_push --> check_bound
+    check_bound -->|no: unbound, selector: none, or no check: line| git_log_shas
+    check_bound -->|yes| check_rules
+    check_rules --> check_result
+    check_result -->|exit 0, nothing the change breaks| git_log_shas
+    check_result -->|exit 0, rules the change breaks| fix_rule_breaks
+    check_result -->|non-zero exit: noted for the return| git_log_shas
+    fix_rule_breaks --> git_log_shas
     git_log_shas --> run_field_set_commits
     run_field_set_commits --> implement_done
     run_stage_fail --> stage_failed
diff --git a/plugins/mattstack/attachments/pipeline/stage-implement/rule-selector.block.md b/plugins/mattstack/attachments/pipeline/stage-implement/rule-selector.block.md
new file mode 100644
index 0000000000..4e51b4d122
--- /dev/null
+++ b/plugins/mattstack/attachments/pipeline/stage-implement/rule-selector.block.md
@@ -0,0 +1,45 @@
+---
+node: check_rules
+props:
+  rule-selector:
+    merge: replace
+    default: ""
+    contract: "rule-selector@1"
+---
+
+# Check the work against the team's rules
+
+The pack's rule selector is the text after the italic line at the end of
+this section; an unbound slot leaves it empty. Resolve it now, on this
+run, since it may consult settings or the environment. It resolves to the
+single line `selector: none`, or to `selector:`, `verdicts:` and `fence:`
+lines with an optional fourth, `check: <command template>`. Only the
+`check:` line matters here. Skip this step (the `no` edge of Does the rule
+selector resolve to a check line?) when the text is empty, resolves to
+`selector: none`, or has no `check:` line.
+
+With a `check:` line:
+
+1. Find the branch point the way self-review does: `git merge-base
+   origin/HEAD HEAD`, or the default branch by name when `origin/HEAD` is
+   unset.
+2. Replace `{base}` in the command with that sha and run it once on Bash,
+   in the worktree, with nothing on stdin. Capture its stdout and its exit
+   status.
+3. Read the stdout. It is written for you: the rules that apply to this
+   change and the lines worth a look. Decide, rule by rule, whether the
+   change breaks it.
+
+An exit other than 0 is one observation, never a failure of the stage:
+quote the exit status and the first line of stderr in one line when the
+stage returns to the orchestrator, fix nothing on its account, and record
+the commits.
+
+Run it once. The check never runs again in this stage. Rule verdicts come
+later only where the pack's self-review runs the self-review verb with
+this same selector bound; the default self-review stage reads the diff
+without the rules.
+
+*If a rule below asks for a move this skill's graph marks STOP, take the off-script edge instead.*
+
+{{props.rule-selector}}
diff --git a/plugins/mattstack/attachments/review-rules-select-body/the-contract.block.md b/plugins/mattstack/attachments/review-rules-select-body/the-contract.block.md
index 32267e0e7b..10a5a3351f 100644
--- a/plugins/mattstack/attachments/review-rules-select-body/the-contract.block.md
+++ b/plugins/mattstack/attachments/review-rules-select-body/the-contract.block.md
@@ -18,6 +18,15 @@ shapes.
   - `fence: <info string>`, the tag of the fenced code block the reviewer
     returns its verdict set in.
 
+  An optional fourth line, `check: <command template>`, holds the
+  placeholder `{base}`. The implement stage runs it in the worktree with
+  nothing on stdin, `{base}` replaced by the branch point, and reads its
+  stdout as the rules that apply and the lines worth a look; exit 0 means
+  it ran, and any other exit is one observation that never blocks. The
+  review verbs never run it: a fill with a `check:` line is still the
+  three-line shape here. The line is additive, so the contract stays
+  `rule-selector@1`, and a fill without it behaves as before.
+
 **The selection** is the JSON the selector prints. This skill reads only
 its `rules` list: each rule has an `id`, a `severity` (`blocking` or
 `advisory`) and a `summary`.
diff --git a/plugins/mattstack/plugin/skills/extending-a-pack/SKILL.md b/plugins/mattstack/plugin/skills/extending-a-pack/SKILL.md
index 9fdcb032d1..2b42a7a688 100644
--- a/plugins/mattstack/plugin/skills/extending-a-pack/SKILL.md
+++ b/plugins/mattstack/plugin/skills/extending-a-pack/SKILL.md
@@ -384,7 +384,7 @@ metadata:
 ```
 
 `provides` is the prop's contract when it has one (`criteria` takes
-`review-criteria@1`, `rule-selector` takes `rule-selector@1`); a `rules` prop has none, so any `provides` binds.
+`review-criteria@1`, `rule-selector` takes `rule-selector@1`, whose optional `check:` line `stage-implement` runs); a `rules` prop has none, so any `provides` binds.
 
 The body: the rule, its reason, and the decision it changes. The stage
 keeps its own flow; the fill carries only what the team adds.
diff --git a/plugins/mattstack/plugin/skills/extending-a-pack/props.md b/plugins/mattstack/plugin/skills/extending-a-pack/props.md
index 06267d0e82..5243ee3ded 100644
--- a/plugins/mattstack/plugin/skills/extending-a-pack/props.md
+++ b/plugins/mattstack/plugin/skills/extending-a-pack/props.md
@@ -74,7 +74,7 @@ block. One fill may bind to any number of blocks.
 | MR preflight, fast checks, commit shape, description shape, labels | `stage-ship` and `ship`: the step blocks below, `domain-rules` |
 | CI job names, retry rules, triage | `stage-watch-ci` and `watch-ci`: `classify-triage-report`, `domain-rules`, `forge` |
 | what reviewers check | `review`, `self-review`, `receive-review`: `criteria` |
-| which written rules a review is checked against, one verdict per rule | `review`, `self-review`, `receive-review`: `rule-selector` |
+| which written rules a review is checked against, one verdict per rule; the check implement runs before self-review | `review`, `self-review`, `receive-review`, `stage-implement`: `rule-selector` |
 | how to answer review threads | `receive-review`: `reply-rules` |
 | fan-out rules for parallel agents | `shepherdr`: the root's `rules`, or a step block below |
 
@@ -94,7 +94,7 @@ default. The other props:
 | `work/sub-agent-tiering` | `tiering` | replace | `model-tiering@1` | nothing |
 | `review/criteria`, `self-review/criteria`, `receive-review/criteria` | `criteria` | replace | `review-criteria@1` | nothing |
 | `review/reviewer`, `self-review/reviewer`, `receive-review/reviewer` | `reviewer` | replace | `reviewer-dispatch@1` | nothing |
-| `review/rule-selector`, `self-review/rule-selector`, `receive-review/rule-selector` | `rule-selector` | replace | `rule-selector@1` | empty (no rule selection) |
+| `review/rule-selector`, `self-review/rule-selector`, `receive-review/rule-selector`, `stage-implement/rule-selector` | `rule-selector` | replace | `rule-selector@1` | empty (no rule selection) |
 | `receive-review/reply-rules` | `reply-rules` | replace | `reply-rules@1` | nothing |
 | `shepherdr` | `tiering` | replace | `model-tiering@1` | `mattstack:model-tiering` |
 | `shepherdr` | `strategy` | replace | `execution-strategy@1` | `mattstack:execution-strategy` |
@@ -103,6 +103,8 @@ default. The other props:
 A `rule-selector` fill resolves to `selector: none`, or three lines: `selector:`
 (a command with `{format}`), `verdicts:` (a command with `{selection}` and
 `{verdicts}`) and `fence:` (the info string of the reviewer's verdict block).
+It may add an optional fourth line, `check: <command template>` with `{base}`,
+which only `stage-implement` runs; still `rule-selector@1`, since it is additive.
 
 A `shepherdr` door compiles with nothing bound; bind one of its three
 replace props only to swap in the pack's own fill.
diff --git a/plugins/mattstack/skills/shepherdr/SKILL.md b/plugins/mattstack/skills/shepherdr/SKILL.md
index 25f07bcd7f..fe6a6cb9e2 100644
--- a/plugins/mattstack/skills/shepherdr/SKILL.md
+++ b/plugins/mattstack/skills/shepherdr/SKILL.md
@@ -4,14 +4,14 @@ description: "Use when fanning work out across parallel Claude Code agents in he
 allowed-tools:
   - "Bash(*/scripts/pick-account.py:*)"
 metadata:
-  compiled: "mattstack@0.32.32 + mattstack:model-tiering@0.32.32 + mattstack:execution-strategy@0.32.32 + mattstack:cswap-accounts@0.32.32"
+  compiled: "mattstack@0.32.33 + mattstack:model-tiering@0.32.33 + mattstack:execution-strategy@0.32.33 + mattstack:cswap-accounts@0.32.33"
 ---
 
 <!-- compiled by rt skills compile from the sources below; props pre-resolved; to change this file, edit its sources and recompile -->
 
-Pointers here are `@keys`. Resolve them once per run: if you already hold a `skills_resolve` map that covers `mattstack@0.32.32:shepherdr`, use it; otherwise call `skills_resolve {id: "mattstack@0.32.32:shepherdr"}` and use the path it returns for each key, in anything you hand a subagent or a tool too. If it fails, stop and say so; never look for the file another way.
+Pointers here are `@keys`. Resolve them once per run: if you already hold a `skills_resolve` map that covers `mattstack@0.32.33:shepherdr`, use it; otherwise call `skills_resolve {id: "mattstack@0.32.33:shepherdr"}` and use the path it returns for each key, in anything you hand a subagent or a tool too. If it fails, stop and say so; never look for the file another way.
 
-<!-- part: block:shepherdr source=mattstack:shepherdr version=0.32.32 path=attachments/orchestration/shepherdr/index.block.md lines=25-75 -->
+<!-- part: block:shepherdr source=mattstack:shepherdr version=0.32.33 path=attachments/orchestration/shepherdr/index.block.md lines=25-75 -->
 # shepherdr
 
 You are the shepherd: a thin delegator, not a reviewer. You break work into jobs, spawn an agent per job (own herdr pane, own git worktree), present what the daemon pushes, and route small messages between the user and the herd. Model, method and account are policy, answered by the bound skills below; you are transport.
@@ -28,15 +28,15 @@ For herdr CLI mechanics, load the `herdr` skill.
 
 *If a rule below asks for a move this graph marks STOP, take the off-script edge instead.*
 
-<!-- part: prop:shepherdr.tiering binding=mattstack:model-tiering version=0.32.32 path=skills/model-tiering/SKILL.md lines=8-164 -->
-For tiering, invoke the `mattstack:model-tiering` skill (mattstack:model-tiering@0.32.32) when this flow needs it.
+<!-- part: prop:shepherdr.tiering binding=mattstack:model-tiering version=0.32.33 path=skills/model-tiering/SKILL.md lines=8-164 -->
+For tiering, invoke the `mattstack:model-tiering` skill (mattstack:model-tiering@0.32.33) when this flow needs it.
 
-<!-- part: block:shepherdr source=mattstack:shepherdr version=0.32.32 path=attachments/orchestration/shepherdr/index.block.md lines=43-75 -->
+<!-- part: block:shepherdr source=mattstack:shepherdr version=0.32.33 path=attachments/orchestration/shepherdr/index.block.md lines=43-75 -->
 ## Strategy
 
 *If a rule below asks for a move this graph marks STOP, take the off-script edge instead.*
 
-<!-- part: prop:shepherdr.strategy binding=mattstack:execution-strategy version=0.32.32 path=attachments/execution-strategy/SKILL.md lines=8-96 -->
+<!-- part: prop:shepherdr.strategy binding=mattstack:execution-strategy version=0.32.33 path=attachments/execution-strategy/SKILL.md lines=8-96 -->
 ### Execution Strategy
 
 Given a unit of work and the surface it will execute on, name the method
@@ -127,7 +127,7 @@ for you -- name the strategy and pass it, nothing more. Either way, do not
 compose method prose per job; the bodies carry the worker-boundary rules
 and the report contract.
 
-<!-- part: block:shepherdr source=mattstack:shepherdr version=0.32.32 path=attachments/orchestration/shepherdr/index.block.md lines=49-75 -->
+<!-- part: block:shepherdr source=mattstack:shepherdr version=0.32.33 path=attachments/orchestration/shepherdr/index.block.md lines=49-75 -->
 ## Domain rules
 
 Domain rules are optional: a pack binds them here or at a step. Bound
@@ -141,7 +141,7 @@ names keeps this skill's default as written.
 
 *A domain rule sits here or in its step's own section; if one asks for a move this graph marks STOP, take the off-script edge instead.*
 
-<!-- part: block:shepherdr source=mattstack:shepherdr version=0.32.32 path=attachments/orchestration/shepherdr/index.block.md lines=64-75 -->
+<!-- part: block:shepherdr source=mattstack:shepherdr version=0.32.33 path=attachments/orchestration/shepherdr/index.block.md lines=64-75 -->
 ## Accounts
 
 *If a rule below asks for a move this graph marks STOP, take the off-script edge instead.*
@@ -153,7 +153,7 @@ question, the per-spawn pick (passed as `account` on `herd_spawn` or
 `herd_respawn`), and the exhaustion decision tree. Accounts in use are
 each job's `account` in `herd_status`, never memory.
 
-<!-- part: prop:shepherdr.accounts binding=mattstack:cswap-accounts version=0.32.32 path=attachments/cswap-accounts/SKILL.md lines=11-77 -->
+<!-- part: prop:shepherdr.accounts binding=mattstack:cswap-accounts version=0.32.33 path=attachments/cswap-accounts/SKILL.md lines=11-77 -->
 ### cswap account pool
 
 Given the herd's model mix and the accounts already assigned this run,
@@ -222,7 +222,7 @@ cache is a shared symlink), so a worker pane missing a plugin's tools is a
 real failure: check the pane's plugin list and the shared cache instead of
 dismissing it.
 
-<!-- part: block:shepherdr/start-and-spawn source=mattstack:shepherdr version=0.32.32 path=attachments/orchestration/shepherdr/start-and-spawn/index.block.md lines=5-95 -->
+<!-- part: block:shepherdr/start-and-spawn source=mattstack:shepherdr version=0.32.33 path=attachments/orchestration/shepherdr/start-and-spawn/index.block.md lines=5-95 -->
 ## Start and spawn
 
 Walk this graph from the trigger; a move it does not show goes to the shepherd off-script gate.
@@ -318,7 +318,7 @@ digraph shepherdr_start {
 }
 ```
 
-<!-- part: block:shepherdr/start-and-spawn/specify-jobs source=mattstack:shepherdr version=0.32.32 path=attachments/orchestration/shepherdr/start-and-spawn/specify-jobs.block.md lines=9-38 -->
+<!-- part: block:shepherdr/start-and-spawn/specify-jobs source=mattstack:shepherdr version=0.32.33 path=attachments/orchestration/shepherdr/start-and-spawn/specify-jobs.block.md lines=9-38 -->
 ### Specify the jobs
 
 **Domain hook -- intake.** Unbound: the jobs are what the user hands you;
@@ -348,7 +348,7 @@ keep it out of the user's checkout, and the delegator rules then do not
 apply. Apply the bound rules' single-worker exception if they name one.
 A later job for a live herd is never this case.
 
-<!-- part: block:shepherdr/start-and-spawn/ask-strategy-model source=mattstack:shepherdr version=0.32.32 path=attachments/orchestration/shepherdr/start-and-spawn/ask-strategy-model.block.md lines=11-37 -->
+<!-- part: block:shepherdr/start-and-spawn/ask-strategy-model source=mattstack:shepherdr version=0.32.33 path=attachments/orchestration/shepherdr/start-and-spawn/ask-strategy-model.block.md lines=11-37 -->
 ### Ask the strategy and model per job
 
 Strategy predicts the work shape, and the shape predicts the tier: one
@@ -375,13 +375,13 @@ the strategy (its method skill is the brief's Method); the recommendation
 starts at the floor, the pin is a fixed half, and a spawn below the floor
 is wrong.
 
-<!-- part: block:shepherdr/start-and-spawn/ask-account-pool source=mattstack:shepherdr version=0.32.32 path=attachments/orchestration/shepherdr/start-and-spawn/ask-account-pool.block.md lines=6-9 -->
+<!-- part: block:shepherdr/start-and-spawn/ask-account-pool source=mattstack:shepherdr version=0.32.33 path=attachments/orchestration/shepherdr/start-and-spawn/ask-account-pool.block.md lines=6-9 -->
 ### Ask the account pool question
 
 Ask it once per herd, after the models are chosen: per-model pools
 hide headroom until the model mix is known. A later job for a live herd keeps the herd's pool answer. The Accounts section says when there is no question to ask.
 
-<!-- part: block:shepherdr/start-and-spawn/collect-repo-conventions source=mattstack:shepherdr version=0.32.32 path=attachments/orchestration/shepherdr/start-and-spawn/collect-repo-conventions.block.md lines=9-31 -->
+<!-- part: block:shepherdr/start-and-spawn/collect-repo-conventions source=mattstack:shepherdr version=0.32.33 path=attachments/orchestration/shepherdr/start-and-spawn/collect-repo-conventions.block.md lines=9-31 -->
 ### Collect the repo conventions
 
 A herd pane is a real `claude` session in a git worktree: user-level
@@ -404,7 +404,7 @@ rules' method skill owns the conventions, `Repo conventions` names only the
 branch; a brief that restates gates, process or evidence competes with the
 worker's skill chain.
 
-<!-- part: block:shepherdr/start-and-spawn/fix-refusal source=mattstack:shepherdr version=0.32.32 path=attachments/orchestration/shepherdr/start-and-spawn/fix-refusal.block.md lines=5-12 -->
+<!-- part: block:shepherdr/start-and-spawn/fix-refusal source=mattstack:shepherdr version=0.32.33 path=attachments/orchestration/shepherdr/start-and-spawn/fix-refusal.block.md lines=5-12 -->
 ### Fix what the refusal names
 
 - **An unfilled marker**: the refusal lists the leftover slots; add a `fill` entry for each.
@@ -414,7 +414,7 @@ worker's skill chain.
 Never copy the template or the strategies file elsewhere to get past a
 refusal; the retry budget hands a stubborn one to the off-script gate.
 
-<!-- part: block:shepherdr/start-and-spawn/shepherd-off-script source=mattstack:shepherdr version=0.32.32 path=attachments/orchestration/shepherdr/start-and-spawn/shepherd-off-script.block.md lines=7-25 -->
+<!-- part: block:shepherdr/start-and-spawn/shepherd-off-script source=mattstack:shepherdr version=0.32.33 path=attachments/orchestration/shepherdr/start-and-spawn/shepherd-off-script.block.md lines=7-25 -->
 ### Shepherd off-script gate: ask the user
 
 Every unresolved refusal and spent budget, in all three graphs, lands
@@ -435,13 +435,13 @@ never a count from memory. A
 same-turn retry count kept in your head, since no daemon budget covers it;
 it answers yes once two retries have run.
 
-<!-- part: block:shepherdr/start-and-spawn/make-recorded-move source=mattstack:shepherdr version=0.32.32 path=attachments/orchestration/shepherdr/start-and-spawn/make-recorded-move.block.md lines=5-8 -->
+<!-- part: block:shepherdr/start-and-spawn/make-recorded-move source=mattstack:shepherdr version=0.32.33 path=attachments/orchestration/shepherdr/start-and-spawn/make-recorded-move.block.md lines=5-8 -->
 ### Make the recorded move once
 
 Make exactly the move the user took, once, as its value spells it. If it
 fails too, that is a new off-script gate, never a retry of your own.
 
-<!-- part: block:shepherdr/what-the-start-graph-cannot-show source=mattstack:shepherdr version=0.32.32 path=attachments/orchestration/shepherdr/what-the-start-graph-cannot-show.block.md lines=9-85 -->
+<!-- part: block:shepherdr/what-the-start-graph-cannot-show source=mattstack:shepherdr version=0.32.33 path=attachments/orchestration/shepherdr/what-the-start-graph-cannot-show.block.md lines=9-85 -->
 ## What the start graph cannot show
 
 **The herd contract.** Every herd is an rt daemon registry row plus one
@@ -518,7 +518,7 @@ off-script gate.
 - **Stagger 4+ spawns**: spawn one, confirm it returned, spawn the next.
 - Agents never work in the user's checkout; skip isolation only for read-only jobs or when the user says to work in place. The worker's directory must be a **linked worktree**, which `herd_spawn` guarantees.
 
-<!-- part: block:shepherdr/the-watch-loop source=mattstack:shepherdr version=0.32.32 path=attachments/orchestration/shepherdr/the-watch-loop/index.block.md lines=5-168 -->
+<!-- part: block:shepherdr/the-watch-loop source=mattstack:shepherdr version=0.32.33 path=attachments/orchestration/shepherdr/the-watch-loop/index.block.md lines=5-168 -->
 ## The watch loop
 
 After the spawns, do nothing until something arrives.
@@ -687,7 +687,7 @@ digraph shepherdr_watch {
 }
 ```
 
-<!-- part: block:shepherdr/the-watch-loop/end-turn-wait source=mattstack:shepherdr version=0.32.32 path=attachments/orchestration/shepherdr/the-watch-loop/end-turn-wait.block.md lines=5-10 -->
+<!-- part: block:shepherdr/the-watch-loop/end-turn-wait source=mattstack:shepherdr version=0.32.33 path=attachments/orchestration/shepherdr/the-watch-loop/end-turn-wait.block.md lines=5-10 -->
 ### End the turn until something arrives
 
 The daemon pushes gates and room lines; nothing arms, and you never read a
@@ -695,7 +695,7 @@ pane or scrollback. Your room posts
 deliver as `@here` and wake every worker, so a question for one worker is a
 DM.
 
-<!-- part: block:shepherdr/the-watch-loop/present-open-gates source=mattstack:shepherdr version=0.32.32 path=attachments/orchestration/shepherdr/the-watch-loop/present-open-gates.block.md lines=6-27 -->
+<!-- part: block:shepherdr/the-watch-loop/present-open-gates source=mattstack:shepherdr version=0.32.33 path=attachments/orchestration/shepherdr/the-watch-loop/present-open-gates.block.md lines=6-27 -->
 ### Present the open gates
 
 Present up to 4 open gates in one AskUserQuestion call. Options are the
@@ -719,36 +719,36 @@ with `writeIn`, else ask them to pick. When the user parks a gate,
 from the job's `herd_status` row: `lastGate`, with `lastGateStatus:
 parked`; relay it verbatim.
 
-<!-- part: block:shepherdr/the-watch-loop/say-which-answer source=mattstack:shepherdr version=0.32.32 path=attachments/orchestration/shepherdr/the-watch-loop/say-which-answer.block.md lines=5-7 -->
+<!-- part: block:shepherdr/the-watch-loop/say-which-answer source=mattstack:shepherdr version=0.32.33 path=attachments/orchestration/shepherdr/the-watch-loop/say-which-answer.block.md lines=5-7 -->
 ### Say which answer won, in one line
 
 Name `winner.answers` and `winner.by`; never re-ask.
 
-<!-- part: block:shepherdr/the-watch-loop/fix-answers-verbatim source=mattstack:shepherdr version=0.32.32 path=attachments/orchestration/shepherdr/the-watch-loop/fix-answers-verbatim.block.md lines=5-7 -->
+<!-- part: block:shepherdr/the-watch-loop/fix-answers-verbatim source=mattstack:shepherdr version=0.32.33 path=attachments/orchestration/shepherdr/the-watch-loop/fix-answers-verbatim.block.md lines=5-7 -->
 ### Fix the answers: each value verbatim
 
 Resend each value from `invalid[].validValues`, verbatim.
 
-<!-- part: block:shepherdr/the-watch-loop/pick-account-by-rules source=mattstack:shepherdr version=0.32.32 path=attachments/orchestration/shepherdr/the-watch-loop/pick-account-by-rules.block.md lines=5-8 -->
+<!-- part: block:shepherdr/the-watch-loop/pick-account-by-rules source=mattstack:shepherdr version=0.32.33 path=attachments/orchestration/shepherdr/the-watch-loop/pick-account-by-rules.block.md lines=5-8 -->
 ### Pick the account per the accounts rules
 
 The Accounts section decides whether to respawn now or ask first; its
 pick is the `account` on `herd_respawn`. Announce the respawn.
 
-<!-- part: block:shepherdr/the-watch-loop/report-stall source=mattstack:shepherdr version=0.32.32 path=attachments/orchestration/shepherdr/the-watch-loop/report-stall.block.md lines=5-8 -->
+<!-- part: block:shepherdr/the-watch-loop/report-stall source=mattstack:shepherdr version=0.32.33 path=attachments/orchestration/shepherdr/the-watch-loop/report-stall.block.md lines=5-8 -->
 ### Report the stall to the user
 
 An expired login with no smart-distribute pool: only the user's
 `/login` fixes it. Name the job, its pane and the verdict.
 
-<!-- part: block:shepherdr/the-watch-loop/ask-attend-respawn source=mattstack:shepherdr version=0.32.32 path=attachments/orchestration/shepherdr/the-watch-loop/ask-attend-respawn.block.md lines=7-11 -->
+<!-- part: block:shepherdr/the-watch-loop/ask-attend-respawn source=mattstack:shepherdr version=0.32.33 path=attachments/orchestration/shepherdr/the-watch-loop/ask-attend-respawn.block.md lines=7-11 -->
 ### Ask: attend or respawn
 
 A dialog the watchdog could not clear parks the job (`stuck-at-modal`).
 **Attend** opens the pane for the user; **Respawn** reuses the stored
 brief.
 
-<!-- part: block:shepherdr/the-watch-loop/point-user-at-tab source=mattstack:shepherdr version=0.32.32 path=attachments/orchestration/shepherdr/the-watch-loop/point-user-at-tab.block.md lines=5-11 -->
+<!-- part: block:shepherdr/the-watch-loop/point-user-at-tab source=mattstack:shepherdr version=0.32.33 path=attachments/orchestration/shepherdr/the-watch-loop/point-user-at-tab.block.md lines=5-11 -->
 ### Point the user at the job's tab
 
 The job's pane in `herd_status` has no `bg:` prefix: the herd is visible,
@@ -757,20 +757,20 @@ which opens tabs only for a hidden herd's panes, would refuse. Tell the
 user in one message which job, its pane ref and tab, and what waits on
 them (the diagnosis reason, or the parked dialog).
 
-<!-- part: block:shepherdr/the-watch-loop/report-crash source=mattstack:shepherdr version=0.32.32 path=attachments/orchestration/shepherdr/the-watch-loop/report-crash.block.md lines=5-8 -->
+<!-- part: block:shepherdr/the-watch-loop/report-crash source=mattstack:shepherdr version=0.32.33 path=attachments/orchestration/shepherdr/the-watch-loop/report-crash.block.md lines=5-8 -->
 ### Report the crash with its job and pane
 
 The pane died with the job live. Tell the user both; never respawn
 silently.
 
-<!-- part: block:shepherdr/the-watch-loop/ask-finish-kill-hold source=mattstack:shepherdr version=0.32.32 path=attachments/orchestration/shepherdr/the-watch-loop/ask-finish-kill-hold.block.md lines=7-11 -->
+<!-- part: block:shepherdr/the-watch-loop/ask-finish-kill-hold source=mattstack:shepherdr version=0.32.33 path=attachments/orchestration/shepherdr/the-watch-loop/ask-finish-kill-hold.block.md lines=7-11 -->
 ### Ask: let them finish, kill and respawn, or hold
 
 One sentence naming the running agents, then the bare three options:
 **Let them finish** (recommended) / **Kill and respawn with the new
 briefs** / **Hold**. No restated heading, no per-option descriptions.
 
-<!-- part: block:shepherdr/what-the-watch-loop-cannot-show source=mattstack:shepherdr version=0.32.32 path=attachments/orchestration/shepherdr/what-the-watch-loop-cannot-show.block.md lines=5-32 -->
+<!-- part: block:shepherdr/what-the-watch-loop-cannot-show source=mattstack:shepherdr version=0.32.33 path=attachments/orchestration/shepherdr/what-the-watch-loop-cannot-show.block.md lines=5-32 -->
 ## What the watch loop cannot show
 
 - **The push is transport.** A gate push is one line, `[gate] <id> is now open; re-read the gate registry.`, carrying only an id. Its arrival proves the daemon, the subscription and the herd; the `herd_gates` read is the verification, made first. `herd_gates` defaults to `HERD_ID` or the sole active herd and also returns open pipeline-run gates in a herd job's worktree. Room lines arrive the same way (`<job> #<n>: <body>` a report, `<job> #<n>: milestone: <artifact>` a milestone). A stale id or an unrelated room line is normal, never a reason to reach for another command or distrust the push.
@@ -800,7 +800,7 @@ brief unless `brief` is new, and keeps the job's model, effort and account
 unless passed. The old session's open and parked gates close as abandoned so the new
 worker re-asks; answered ones are marked consumed.
 
-<!-- part: block:shepherdr/lanes-and-wrap-up source=mattstack:shepherdr version=0.32.32 path=attachments/orchestration/shepherdr/lanes-and-wrap-up/index.block.md lines=5-119 -->
+<!-- part: block:shepherdr/lanes-and-wrap-up source=mattstack:shepherdr version=0.32.33 path=attachments/orchestration/shepherdr/lanes-and-wrap-up/index.block.md lines=5-119 -->
 ## Lanes and wrap-up
 
 ```dot
@@ -920,13 +920,13 @@ digraph shepherdr_lanes {
 }
 ```
 
-<!-- part: block:shepherdr/lanes-and-wrap-up/flag-drift-collision source=mattstack:shepherdr version=0.32.32 path=attachments/orchestration/shepherdr/lanes-and-wrap-up/flag-drift-collision.block.md lines=5-8 -->
+<!-- part: block:shepherdr/lanes-and-wrap-up/flag-drift-collision source=mattstack:shepherdr version=0.32.33 path=attachments/orchestration/shepherdr/lanes-and-wrap-up/flag-drift-collision.block.md lines=5-8 -->
 ### Flag the drift or collision to the user
 
 Files outside the job's write fence are drift; a file two jobs changed is
 a collision. Flag it now, not at integration.
 
-<!-- part: block:shepherdr/lanes-and-wrap-up/relay-measured-only source=mattstack:shepherdr version=0.32.32 path=attachments/orchestration/shepherdr/lanes-and-wrap-up/relay-measured-only.block.md lines=5-10 -->
+<!-- part: block:shepherdr/lanes-and-wrap-up/relay-measured-only source=mattstack:shepherdr version=0.32.33 path=attachments/orchestration/shepherdr/lanes-and-wrap-up/relay-measured-only.block.md lines=5-10 -->
 ### Relay only what you measured
 
 A worker's claims about its environment (servers up, ports free, CI green)
@@ -934,7 +934,7 @@ are routinely stale. Measure first
 (`rt_verb {args: ["endpoint", "lookup", "<role>", "--path", "<the job's worktree>"]}`,
 `curl`, `lsof`, a CI status call), or attribute it: "the worker reports X".
 
-<!-- part: block:shepherdr/lanes-and-wrap-up/ask-integration-strategy source=mattstack:shepherdr version=0.32.32 path=attachments/orchestration/shepherdr/lanes-and-wrap-up/ask-integration-strategy.block.md lines=6-11 -->
+<!-- part: block:shepherdr/lanes-and-wrap-up/ask-integration-strategy source=mattstack:shepherdr version=0.32.33 path=attachments/orchestration/shepherdr/lanes-and-wrap-up/ask-integration-strategy.block.md lines=6-11 -->
 ### Ask the integration job's strategy and model
 
 One AskUserQuestion like every job's: the tier table's integration row is
@@ -942,14 +942,14 @@ the recommendation, the strategy half from the strategy table. Keep the
 herd's pool answer and pass the Accounts section's per-spawn pick as
 `account`.
 
-<!-- part: block:shepherdr/lanes-and-wrap-up/gate-merge-lane source=mattstack:shepherdr version=0.32.32 path=attachments/orchestration/shepherdr/lanes-and-wrap-up/gate-merge-lane.block.md lines=7-11 -->
+<!-- part: block:shepherdr/lanes-and-wrap-up/gate-merge-lane source=mattstack:shepherdr version=0.32.33 path=attachments/orchestration/shepherdr/lanes-and-wrap-up/gate-merge-lane.block.md lines=7-11 -->
 ### Gate: merge this lane?
 
 Only when bound domain rules give the shepherd the merge. One sentence
 with the PR or MR link, its state and its CI, then **Merge** / **Not yet** /
 **Hold**.
 
-<!-- part: block:shepherdr/lanes-and-wrap-up/flip-lane-ticket source=mattstack:shepherdr version=0.32.32 path=attachments/orchestration/shepherdr/lanes-and-wrap-up/flip-lane-ticket.block.md lines=5-11 -->
+<!-- part: block:shepherdr/lanes-and-wrap-up/flip-lane-ticket source=mattstack:shepherdr version=0.32.33 path=attachments/orchestration/shepherdr/lanes-and-wrap-up/flip-lane-ticket.block.md lines=5-11 -->
 ### Flip the lane's ticket, when it has one
 
 Flip it just before `herd_close`, for each lane an integration report
@@ -958,7 +958,7 @@ merges. Only you close a done job's pane. The watchdog nags past
 skipped; for a lane awaiting the integration job or a merge gate it is
 normal, so end the turn.
 
-<!-- part: block:shepherdr/lanes-and-wrap-up/show-status-table source=mattstack:shepherdr version=0.32.32 path=attachments/orchestration/shepherdr/lanes-and-wrap-up/show-status-table.block.md lines=5-14 -->
+<!-- part: block:shepherdr/lanes-and-wrap-up/show-status-table source=mattstack:shepherdr version=0.32.33 path=attachments/orchestration/shepherdr/lanes-and-wrap-up/show-status-table.block.md lines=5-14 -->
 ### Show the status table
 
 Reformat `herd_status {herd}`, flagging failures and the latest
@@ -970,7 +970,7 @@ Reformat `herd_status {herd}`, flagging failures and the latest
 | api tests | w3:p1 | 2 | direct-tdd | done | A1-A4 done, 12 tests, suite green |
 ```
 
-<!-- part: block:shepherdr/lanes-and-wrap-up/gate-wrap-up-form source=mattstack:shepherdr version=0.32.32 path=attachments/orchestration/shepherdr/lanes-and-wrap-up/gate-wrap-up-form.block.md lines=7-18 -->
+<!-- part: block:shepherdr/lanes-and-wrap-up/gate-wrap-up-form source=mattstack:shepherdr version=0.32.33 path=attachments/orchestration/shepherdr/lanes-and-wrap-up/gate-wrap-up-form.block.md lines=7-18 -->
 ### Gate wrap-up: the form contract
 
 One form, per the wrap-up form contract below:
@@ -984,7 +984,7 @@ One form, per the wrap-up form contract below:
 Never auto-remove a tree or job dir; `herd_wrap_up` executes exactly the
 form's answer.
 
-<!-- part: block:shepherdr/lanes-and-wrap-up/measure-running source=mattstack:shepherdr version=0.32.32 path=attachments/orchestration/shepherdr/lanes-and-wrap-up/measure-running.block.md lines=5-23 -->
+<!-- part: block:shepherdr/lanes-and-wrap-up/measure-running source=mattstack:shepherdr version=0.32.33 path=attachments/orchestration/shepherdr/lanes-and-wrap-up/measure-running.block.md lines=5-23 -->
 ### Measure what still runs
 
 The stop calls cover every job in the dispose list or with a closing pane:
@@ -1005,13 +1005,13 @@ Measure before you say a job's servers stopped (`lsof -ti tcp:<port>` or
 the endpoint lookup). Report a survivor as still running, never kill it by
 hand, and anything unmeasured as "not verified".
 
-<!-- part: block:shepherdr/lanes-and-wrap-up/report-refusal source=mattstack:shepherdr version=0.32.32 path=attachments/orchestration/shepherdr/lanes-and-wrap-up/report-refusal.block.md lines=5-8 -->
+<!-- part: block:shepherdr/lanes-and-wrap-up/report-refusal source=mattstack:shepherdr version=0.32.33 path=attachments/orchestration/shepherdr/lanes-and-wrap-up/report-refusal.block.md lines=5-8 -->
 ### Report the refusal in the guard's words
 
 Quote the disposal refusal as the guard gave it. In hidden mode, also offer
 the Bash command `rt herd stop --hidden` (no tool runs it); never run it unprompted. <!-- mcp-lint: allow -->
 
-<!-- part: block:shepherdr/what-the-lanes-graph-cannot-show source=mattstack:shepherdr version=0.32.32 path=attachments/orchestration/shepherdr/what-the-lanes-graph-cannot-show.block.md lines=9-18 -->
+<!-- part: block:shepherdr/what-the-lanes-graph-cannot-show source=mattstack:shepherdr version=0.32.33 path=attachments/orchestration/shepherdr/what-the-lanes-graph-cannot-show.block.md lines=9-18 -->
 ## What the lanes graph cannot show
 
 - **The two objective checks.** `herd_lanes {herd}` returns a row per active job (`commits`; `drift.files`, committed and uncommitted work since the merge base; `collidesWith`) plus herd-wide `collisions`. Compare each job's `drift.files` against its write fence yourself; no fence is stored. A job whose tree is gone has no row (it is in `skipped` with a reason), and the drift check skips it.
@@ -1021,12 +1021,12 @@ the Bash command `rt herd stop --hidden` (no tool runs it); never run it unpromp
 - **Domain hook: after the report.** Unbound: the integration job merges. Bound domain rules may define what follows a report (the worker ships through its own skill chain, the shepherd merges after a gate, or a human merges on the forge and the lane closes when `herd_lanes` reads `merged`; how jobs feeding one deliverable integrate) and whether it waits for the user to ask. Fixing and pushing stay with workers.
 - **Domain hook: wrap-up.** Unbound: as drawn. Bound domain rules may state their own tree lifecycle (trees that dispose themselves on merge, what a disposal refusal means); follow it over the defaults here.
 
-<!-- part: block:shepherdr/wrap-up-form-contract source=mattstack:shepherdr version=0.32.32 path=attachments/orchestration/shepherdr/wrap-up-form-contract.block.md lines=6-10 -->
+<!-- part: block:shepherdr/wrap-up-form-contract source=mattstack:shepherdr version=0.32.33 path=attachments/orchestration/shepherdr/wrap-up-form-contract.block.md lines=6-10 -->
 ## wrap-up form contract
 
 *If a rule below asks for a move this graph marks STOP, take the off-script edge instead.*
 
-<!-- part: block:wrap-up-form source=mattstack:wrap-up-form version=0.32.32 path=attachments/wrap-up-form/index.block.md lines=7-33 -->
+<!-- part: block:wrap-up-form source=mattstack:wrap-up-form version=0.32.33 path=attachments/wrap-up-form/index.block.md lines=7-33 -->
 ### Wrap-up
 
 The reply is one optional sentence of context, then a form, then stop. Wait
@@ -1055,7 +1055,7 @@ next call after the answers return, never into the context sentence.
 | "I can hand them a default to save them answering" | Recommended options already do that in the form; a typed reply still costs more than a tap and leaves no record of the pick. |
 | "The context sentence, then a line introducing the form" | Two sentences. The form needs no introduction; the sentence is the whole preamble. |
 
-<!-- part: block:shepherdr/rationalizations source=mattstack:shepherdr version=0.32.32 path=attachments/orchestration/shepherdr/rationalizations.block.md lines=5-24 -->
+<!-- part: block:shepherdr/rationalizations source=mattstack:shepherdr version=0.32.33 path=attachments/orchestration/shepherdr/rationalizations.block.md lines=5-24 -->
 ## Rationalizations
 
 | Thought | Reality |
diff --git a/plugins/mattstack/skills/shepherdr/compiled.json b/plugins/mattstack/skills/shepherdr/compiled.json
index c01ffcd4e0..e7fabad9bf 100644
--- a/plugins/mattstack/skills/shepherdr/compiled.json
+++ b/plugins/mattstack/skills/shepherdr/compiled.json
@@ -1,8 +1,8 @@
 {
-  "id": "mattstack@0.32.32:shepherdr",
+  "id": "mattstack@0.32.33:shepherdr",
   "dir": "skills/shepherdr",
   "covers": [
-    "mattstack@0.32.32:shepherdr"
+    "mattstack@0.32.33:shepherdr"
   ],
   "keys": {
     "shepherdr/SKILL.md": "skills/shepherdr/SKILL.md",
diff --git a/plugins/mattstack/skills/wrap-up/SKILL.md b/plugins/mattstack/skills/wrap-up/SKILL.md
index bc6b638e82..1ca0dda6c0 100644
--- a/plugins/mattstack/skills/wrap-up/SKILL.md
+++ b/plugins/mattstack/skills/wrap-up/SKILL.md
@@ -2,12 +2,12 @@
 name: "wrap-up"
 description: "Use when wrapping up a session, checking in before continuing, ending a turn with open decisions, when the user asks what you need from them, what decisions are open, or what the next steps are, when they invoke wrap-up or check-in, or when a pipeline gate needs its decision presented as a form."
 metadata:
-  compiled: "mattstack@0.32.32"
+  compiled: "mattstack@0.32.33"
 ---
 
 <!-- compiled by rt skills compile from the sources below; props pre-resolved; to change this file, edit its sources and recompile -->
 
-<!-- part: block:wrap-up-form source=mattstack:wrap-up-form version=0.32.32 path=attachments/wrap-up-form/index.block.md lines=7-33 -->
+<!-- part: block:wrap-up-form source=mattstack:wrap-up-form version=0.32.33 path=attachments/wrap-up-form/index.block.md lines=7-33 -->
 # Wrap-up
 
 The reply is one optional sentence of context, then a form, then stop. Wait
diff --git a/plugins/mattstack/skills/wrap-up/compiled.json b/plugins/mattstack/skills/wrap-up/compiled.json
index 3a7782891a..bd0645a34c 100644
--- a/plugins/mattstack/skills/wrap-up/compiled.json
+++ b/plugins/mattstack/skills/wrap-up/compiled.json
@@ -1,8 +1,8 @@
 {
-  "id": "mattstack@0.32.32:wrap-up",
+  "id": "mattstack@0.32.33:wrap-up",
   "dir": "skills/wrap-up",
   "covers": [
-    "mattstack@0.32.32:wrap-up"
+    "mattstack@0.32.33:wrap-up"
   ],
   "keys": {}
 }
diff --git a/plugins/mattstack/skills/writing-style-conversational/SKILL.md b/plugins/mattstack/skills/writing-style-conversational/SKILL.md
index 5c6868f0e4..923b22b838 100644
--- a/plugins/mattstack/skills/writing-style-conversational/SKILL.md
+++ b/plugins/mattstack/skills/writing-style-conversational/SKILL.md
@@ -2,27 +2,27 @@
 name: "writing-style-conversational"
 description: "Use only when the mattstack writing-style lookup names mattstack:writing-style-conversational, or falls back to it because the lookup failed or the skill it named will not load. The voice for review comments, replies, PR descriptions and commit messages posted under the operator's name: short, friendly sentences in sentence case, like talking to a teammate."
 metadata:
-  compiled: "mattstack@0.32.32"
+  compiled: "mattstack@0.32.33"
 ---
 
 <!-- compiled by rt skills compile from the sources below; props pre-resolved; to change this file, edit its sources and recompile -->
 
-Pointers here are `@keys`. Resolve them once per run: if you already hold a `skills_resolve` map that covers `mattstack@0.32.32:writing-style-conversational`, use it; otherwise call `skills_resolve {id: "mattstack@0.32.32:writing-style-conversational"}` and use the path it returns for each key, in anything you hand a subagent or a tool too. If it fails, stop and say so; never look for the file another way.
+Pointers here are `@keys`. Resolve them once per run: if you already hold a `skills_resolve` map that covers `mattstack@0.32.33:writing-style-conversational`, use it; otherwise call `skills_resolve {id: "mattstack@0.32.33:writing-style-conversational"}` and use the path it returns for each key, in anything you hand a subagent or a tool too. If it fails, stop and say so; never look for the file another way.
 
-<!-- part: block:writing-style-conversational source=mattstack:writing-style-conversational version=0.32.32 path=attachments/writing-style/writing-style-conversational/index.block.md lines=7-12 -->
+<!-- part: block:writing-style-conversational source=mattstack:writing-style-conversational version=0.32.33 path=attachments/writing-style/writing-style-conversational/index.block.md lines=7-12 -->
 # Conversational
 
 Short, friendly, and plain, like talking to a teammate across a desk. Load
 this before the first draft and write in it from the first word.
 
-<!-- part: block:writing-style-floor source=mattstack:writing-style-floor version=0.32.32 path=attachments/writing-style-floor/index.block.md lines=6-10 -->
+<!-- part: block:writing-style-floor source=mattstack:writing-style-floor version=0.32.33 path=attachments/writing-style-floor/index.block.md lines=6-10 -->
 ## Rules every style shares
 
 These bind anything posted under the operator's name: review findings, the
 review summary, replies on their own PR, PR descriptions, commit messages.
 The preset sets the voice; these set the floor.
 
-<!-- part: block:writing-style-floor/never source=mattstack:writing-style-floor version=0.32.32 path=attachments/writing-style-floor/never.block.md lines=5-20 -->
+<!-- part: block:writing-style-floor/never source=mattstack:writing-style-floor version=0.32.33 path=attachments/writing-style-floor/never.block.md lines=5-20 -->
 ### Never
 
 - **Em or en dashes.** Rephrase, or use parentheses, a colon, or an ellipsis
@@ -40,7 +40,7 @@ The preset sets the voice; these set the floor.
   noticed:", "Took a look", "I just wanted to". Start with the claim.
 - **Invented precision.** "most" beats "~96%" unless the number was measured.
 
-<!-- part: block:writing-style-floor/always source=mattstack:writing-style-floor version=0.32.32 path=attachments/writing-style-floor/always.block.md lines=5-35 -->
+<!-- part: block:writing-style-floor/always source=mattstack:writing-style-floor version=0.32.33 path=attachments/writing-style-floor/always.block.md lines=5-35 -->
 ### Always
 
 - **Compress before posting.** The first draft is a rough cut. Before posting
@@ -73,7 +73,7 @@ The preset sets the voice; these set the floor.
   notes. It never recaps a finding, lists strengths, or reports what you ran.
   A finding with no line to anchor to is its own top-level comment.
 
-<!-- part: block:writing-style-conversational/voice source=mattstack:writing-style-conversational version=0.32.32 path=attachments/writing-style/writing-style-conversational/voice.block.md lines=5-17 -->
+<!-- part: block:writing-style-conversational/voice source=mattstack:writing-style-conversational version=0.32.33 path=attachments/writing-style/writing-style-conversational/voice.block.md lines=5-17 -->
 ## Voice
 
 - **Sentence case** everywhere, with contractions.
@@ -88,7 +88,7 @@ The preset sets the voice; these set the floor.
 Compression target: would this read naturally if you said it out loud to the
 author? Cut anything you would not say.
 
-<!-- part: block:writing-style-conversational/review-findings source=mattstack:writing-style-conversational version=0.32.32 path=attachments/writing-style/writing-style-conversational/review-findings.block.md lines=5-24 -->
+<!-- part: block:writing-style-conversational/review-findings source=mattstack:writing-style-conversational version=0.32.33 path=attachments/writing-style/writing-style-conversational/review-findings.block.md lines=5-24 -->
 ## Review findings
 
 Open with a bolded Conventional Comments label, never a code span
@@ -110,13 +110,13 @@ const pageCount = Math.ceil(total / pageSize);
 A process ask is one line that leads with the approval if there is one:
 `**suggestion:** Looks good! Could you add a test for the empty-list case?`
 
-<!-- part: block:writing-style-conversational/review-summary source=mattstack:writing-style-conversational version=0.32.32 path=attachments/writing-style/writing-style-conversational/review-summary.block.md lines=5-8 -->
+<!-- part: block:writing-style-conversational/review-summary source=mattstack:writing-style-conversational version=0.32.33 path=attachments/writing-style/writing-style-conversational/review-summary.block.md lines=5-8 -->
 ## Review summary
 
 One line: `Looks good to me, no blockers. Left a few comments inline.` Only a
 blocker joins it.
 
-<!-- part: block:writing-style-conversational/replies-on-your-own-pr source=mattstack:writing-style-conversational version=0.32.32 path=attachments/writing-style/writing-style-conversational/replies-on-your-own-pr.block.md lines=6-14 -->
+<!-- part: block:writing-style-conversational/replies-on-your-own-pr source=mattstack:writing-style-conversational version=0.32.33 path=attachments/writing-style/writing-style-conversational/replies-on-your-own-pr.block.md lines=6-14 -->
 ## Replies on your own PR
 
 One to three short sentences. No sign-offs; thank someone only if they
@@ -127,12 +127,12 @@ matters.
 - `Good call, switched to Record<Status, string>.`
 - `I'd skip the lock for now. The job runs on one worker, and a lock adds a round trip per write.`
 
-<!-- part: block:writing-style-conversational/pr-descriptions source=mattstack:writing-style-conversational version=0.32.32 path=attachments/writing-style/writing-style-conversational/pr-descriptions.block.md lines=6-8 -->
+<!-- part: block:writing-style-conversational/pr-descriptions source=mattstack:writing-style-conversational version=0.32.33 path=attachments/writing-style/writing-style-conversational/pr-descriptions.block.md lines=6-8 -->
 ## PR descriptions
 
 Read `@writing-style-conversational/pr-description.md` before drafting.
 
-<!-- part: block:writing-style-conversational/commit-messages source=mattstack:writing-style-conversational version=0.32.32 path=attachments/writing-style/writing-style-conversational/commit-messages.block.md lines=5-9 -->
+<!-- part: block:writing-style-conversational/commit-messages source=mattstack:writing-style-conversational version=0.32.33 path=attachments/writing-style/writing-style-conversational/commit-messages.block.md lines=5-9 -->
 ## Commit messages
 
 - Subject: imperative, sentence case, under 72 characters, with the ticket
diff --git a/plugins/mattstack/skills/writing-style-conversational/compiled.json b/plugins/mattstack/skills/writing-style-conversational/compiled.json
index 1387d77b49..7bf853f63e 100644
--- a/plugins/mattstack/skills/writing-style-conversational/compiled.json
+++ b/plugins/mattstack/skills/writing-style-conversational/compiled.json
@@ -1,8 +1,8 @@
 {
-  "id": "mattstack@0.32.32:writing-style-conversational",
+  "id": "mattstack@0.32.33:writing-style-conversational",
   "dir": "skills/writing-style-conversational",
   "covers": [
-    "mattstack@0.32.32:writing-style-conversational"
+    "mattstack@0.32.33:writing-style-conversational"
   ],
   "keys": {
     "writing-style-conversational/pr-description.md": "skills/writing-style-conversational/pr-description.md"
diff --git a/plugins/mattstack/skills/writing-style-sparse/SKILL.md b/plugins/mattstack/skills/writing-style-sparse/SKILL.md
index 44f52bd5df..e966c83dd7 100644
--- a/plugins/mattstack/skills/writing-style-sparse/SKILL.md
+++ b/plugins/mattstack/skills/writing-style-sparse/SKILL.md
@@ -2,28 +2,28 @@
 name: "writing-style-sparse"
 description: "Use only when the mattstack writing-style lookup names mattstack:writing-style-sparse. The voice for review comments, replies, PR descriptions and commit messages posted under the operator's name: terse, lowercase technical prose, one tight paragraph per point."
 metadata:
-  compiled: "mattstack@0.32.32"
+  compiled: "mattstack@0.32.33"
 ---
 
 <!-- compiled by rt skills compile from the sources below; props pre-resolved; to change this file, edit its sources and recompile -->
 
-Pointers here are `@keys`. Resolve them once per run: if you already hold a `skills_resolve` map that covers `mattstack@0.32.32:writing-style-sparse`, use it; otherwise call `skills_resolve {id: "mattstack@0.32.32:writing-style-sparse"}` and use the path it returns for each key, in anything you hand a subagent or a tool too. If it fails, stop and say so; never look for the file another way.
+Pointers here are `@keys`. Resolve them once per run: if you already hold a `skills_resolve` map that covers `mattstack@0.32.33:writing-style-sparse`, use it; otherwise call `skills_resolve {id: "mattstack@0.32.33:writing-style-sparse"}` and use the path it returns for each key, in anything you hand a subagent or a tool too. If it fails, stop and say so; never look for the file another way.
 
-<!-- part: block:writing-style-sparse source=mattstack:writing-style-sparse version=0.32.32 path=attachments/writing-style/writing-style-sparse/index.block.md lines=7-13 -->
+<!-- part: block:writing-style-sparse source=mattstack:writing-style-sparse version=0.32.33 path=attachments/writing-style/writing-style-sparse/index.block.md lines=7-13 -->
 # Sparse
 
 Terse and conversational. The reader is a colleague who can follow a chain
 from one sentence. Load this before the first draft and write in it from the
 first word; it is not a pass applied to a finished draft.
 
-<!-- part: block:writing-style-floor source=mattstack:writing-style-floor version=0.32.32 path=attachments/writing-style-floor/index.block.md lines=6-10 -->
+<!-- part: block:writing-style-floor source=mattstack:writing-style-floor version=0.32.33 path=attachments/writing-style-floor/index.block.md lines=6-10 -->
 ## Rules every style shares
 
 These bind anything posted under the operator's name: review findings, the
 review summary, replies on their own PR, PR descriptions, commit messages.
 The preset sets the voice; these set the floor.
 
-<!-- part: block:writing-style-floor/never source=mattstack:writing-style-floor version=0.32.32 path=attachments/writing-style-floor/never.block.md lines=5-20 -->
+<!-- part: block:writing-style-floor/never source=mattstack:writing-style-floor version=0.32.33 path=attachments/writing-style-floor/never.block.md lines=5-20 -->
 ### Never
 
 - **Em or en dashes.** Rephrase, or use parentheses, a colon, or an ellipsis
@@ -41,7 +41,7 @@ The preset sets the voice; these set the floor.
   noticed:", "Took a look", "I just wanted to". Start with the claim.
 - **Invented precision.** "most" beats "~96%" unless the number was measured.
 
-<!-- part: block:writing-style-floor/always source=mattstack:writing-style-floor version=0.32.32 path=attachments/writing-style-floor/always.block.md lines=5-35 -->
+<!-- part: block:writing-style-floor/always source=mattstack:writing-style-floor version=0.32.33 path=attachments/writing-style-floor/always.block.md lines=5-35 -->
 ### Always
 
 - **Compress before posting.** The first draft is a rough cut. Before posting
@@ -74,7 +74,7 @@ The preset sets the voice; these set the floor.
   notes. It never recaps a finding, lists strengths, or reports what you ran.
   A finding with no line to anchor to is its own top-level comment.
 
-<!-- part: block:writing-style-sparse/voice source=mattstack:writing-style-sparse version=0.32.32 path=attachments/writing-style/writing-style-sparse/voice.block.md lines=5-21 -->
+<!-- part: block:writing-style-sparse/voice source=mattstack:writing-style-sparse version=0.32.33 path=attachments/writing-style/writing-style-sparse/voice.block.md lines=5-21 -->
 ## Voice
 
 - **Lowercase for technical content**: findings, assertions, code talk.
@@ -93,7 +93,7 @@ Compression target: shorter and more conversational. Ask "would a busy
 teammate send this as written, or trim it first?" If there is any doubt,
 trim.
 
-<!-- part: block:writing-style-sparse/review-findings source=mattstack:writing-style-sparse version=0.32.32 path=attachments/writing-style/writing-style-sparse/review-findings.block.md lines=5-49 -->
+<!-- part: block:writing-style-sparse/review-findings source=mattstack:writing-style-sparse version=0.32.33 path=attachments/writing-style/writing-style-sparse/review-findings.block.md lines=5-49 -->
 ## Review findings
 
 Open with a bolded Conventional Comments label, never a code span:
@@ -140,14 +140,14 @@ A brief, specific credit is fine folded in after the worry, never as the
 opener: `**thought (non-blocking):** only worry here: nothing tests the
 fallback. the version's pinned now, nice catch.`. A bare compliment is not.
 
-<!-- part: block:writing-style-sparse/review-summary source=mattstack:writing-style-sparse version=0.32.32 path=attachments/writing-style/writing-style-sparse/review-summary.block.md lines=5-9 -->
+<!-- part: block:writing-style-sparse/review-summary source=mattstack:writing-style-sparse version=0.32.33 path=attachments/writing-style/writing-style-sparse/review-summary.block.md lines=5-9 -->
 ## Review summary
 
 One line, sentence case: `Looks solid to me, no blockers. Left a few inline
 notes.` or `Left a few comments!` Only a blocker may join it: `Left one
 blocker inline.`
 
-<!-- part: block:writing-style-sparse/replies-on-your-own-pr source=mattstack:writing-style-sparse version=0.32.32 path=attachments/writing-style/writing-style-sparse/replies-on-your-own-pr.block.md lines=6-18 -->
+<!-- part: block:writing-style-sparse/replies-on-your-own-pr source=mattstack:writing-style-sparse version=0.32.33 path=attachments/writing-style/writing-style-sparse/replies-on-your-own-pr.block.md lines=6-18 -->
 ## Replies on your own PR
 
 Very short. No sign-offs, no thanks unless they thanked first. Soften even
@@ -162,13 +162,13 @@ blank-line paragraphs.
 - `i don't think we need a lock here. the job runs on one worker, and a lock adds a round trip per write.`
 - `👍`
 
-<!-- part: block:writing-style-sparse/pr-descriptions source=mattstack:writing-style-sparse version=0.32.32 path=attachments/writing-style/writing-style-sparse/pr-descriptions.block.md lines=6-9 -->
+<!-- part: block:writing-style-sparse/pr-descriptions source=mattstack:writing-style-sparse version=0.32.33 path=attachments/writing-style/writing-style-sparse/pr-descriptions.block.md lines=6-9 -->
 ## PR descriptions
 
 Read `@writing-style-sparse/pr-description.md` before drafting. It carries the
 length target, the structure, and the anti-patterns.
 
-<!-- part: block:writing-style-sparse/commit-messages source=mattstack:writing-style-sparse version=0.32.32 path=attachments/writing-style/writing-style-sparse/commit-messages.block.md lines=5-9 -->
+<!-- part: block:writing-style-sparse/commit-messages source=mattstack:writing-style-sparse version=0.32.33 path=attachments/writing-style/writing-style-sparse/commit-messages.block.md lines=5-9 -->
 ## Commit messages
 
 - Subject: lowercase, imperative, under 72 characters, prefixed with the
diff --git a/plugins/mattstack/skills/writing-style-sparse/compiled.json b/plugins/mattstack/skills/writing-style-sparse/compiled.json
index 5ea3305353..f9aea9b342 100644
--- a/plugins/mattstack/skills/writing-style-sparse/compiled.json
+++ b/plugins/mattstack/skills/writing-style-sparse/compiled.json
@@ -1,8 +1,8 @@
 {
-  "id": "mattstack@0.32.32:writing-style-sparse",
+  "id": "mattstack@0.32.33:writing-style-sparse",
   "dir": "skills/writing-style-sparse",
   "covers": [
-    "mattstack@0.32.32:writing-style-sparse"
+    "mattstack@0.32.33:writing-style-sparse"
   ],
   "keys": {
     "writing-style-sparse/pr-description.md": "skills/writing-style-sparse/pr-description.md"
diff --git a/plugins/mattstack/skills/writing-style-structured/SKILL.md b/plugins/mattstack/skills/writing-style-structured/SKILL.md
index e183e0ee19..0caa52d99d 100644
--- a/plugins/mattstack/skills/writing-style-structured/SKILL.md
+++ b/plugins/mattstack/skills/writing-style-structured/SKILL.md
@@ -2,28 +2,28 @@
 name: "writing-style-structured"
 description: "Use only when the mattstack writing-style lookup names mattstack:writing-style-structured. The voice for review comments, replies, PR descriptions and commit messages posted under the operator's name: labelled lines and short bullets for teams that prefer formal write-ups."
 metadata:
-  compiled: "mattstack@0.32.32"
+  compiled: "mattstack@0.32.33"
 ---
 
 <!-- compiled by rt skills compile from the sources below; props pre-resolved; to change this file, edit its sources and recompile -->
 
-Pointers here are `@keys`. Resolve them once per run: if you already hold a `skills_resolve` map that covers `mattstack@0.32.32:writing-style-structured`, use it; otherwise call `skills_resolve {id: "mattstack@0.32.32:writing-style-structured"}` and use the path it returns for each key, in anything you hand a subagent or a tool too. If it fails, stop and say so; never look for the file another way.
+Pointers here are `@keys`. Resolve them once per run: if you already hold a `skills_resolve` map that covers `mattstack@0.32.33:writing-style-structured`, use it; otherwise call `skills_resolve {id: "mattstack@0.32.33:writing-style-structured"}` and use the path it returns for each key, in anything you hand a subagent or a tool too. If it fails, stop and say so; never look for the file another way.
 
-<!-- part: block:writing-style-structured source=mattstack:writing-style-structured version=0.32.32 path=attachments/writing-style/writing-style-structured/index.block.md lines=7-13 -->
+<!-- part: block:writing-style-structured source=mattstack:writing-style-structured version=0.32.33 path=attachments/writing-style/writing-style-structured/index.block.md lines=7-13 -->
 # Structured
 
 Clear and scannable, for teams that like formal write-ups. Every point is
 labelled so a reader can triage without reading the whole thing. Load this
 before the first draft and write in it from the first word.
 
-<!-- part: block:writing-style-floor source=mattstack:writing-style-floor version=0.32.32 path=attachments/writing-style-floor/index.block.md lines=6-10 -->
+<!-- part: block:writing-style-floor source=mattstack:writing-style-floor version=0.32.33 path=attachments/writing-style-floor/index.block.md lines=6-10 -->
 ## Rules every style shares
 
 These bind anything posted under the operator's name: review findings, the
 review summary, replies on their own PR, PR descriptions, commit messages.
 The preset sets the voice; these set the floor.
 
-<!-- part: block:writing-style-floor/never source=mattstack:writing-style-floor version=0.32.32 path=attachments/writing-style-floor/never.block.md lines=5-20 -->
+<!-- part: block:writing-style-floor/never source=mattstack:writing-style-floor version=0.32.33 path=attachments/writing-style-floor/never.block.md lines=5-20 -->
 ### Never
 
 - **Em or en dashes.** Rephrase, or use parentheses, a colon, or an ellipsis
@@ -41,7 +41,7 @@ The preset sets the voice; these set the floor.
   noticed:", "Took a look", "I just wanted to". Start with the claim.
 - **Invented precision.** "most" beats "~96%" unless the number was measured.
 
-<!-- part: block:writing-style-floor/always source=mattstack:writing-style-floor version=0.32.32 path=attachments/writing-style-floor/always.block.md lines=5-35 -->
+<!-- part: block:writing-style-floor/always source=mattstack:writing-style-floor version=0.32.33 path=attachments/writing-style-floor/always.block.md lines=5-35 -->
 ### Always
 
 - **Compress before posting.** The first draft is a rough cut. Before posting
@@ -74,7 +74,7 @@ The preset sets the voice; these set the floor.
   notes. It never recaps a finding, lists strengths, or reports what you ran.
   A finding with no line to anchor to is its own top-level comment.
 
-<!-- part: block:writing-style-structured/voice source=mattstack:writing-style-structured version=0.32.32 path=attachments/writing-style/writing-style-structured/voice.block.md lines=5-15 -->
+<!-- part: block:writing-style-structured/voice source=mattstack:writing-style-structured version=0.32.33 path=attachments/writing-style/writing-style-structured/voice.block.md lines=5-15 -->
 ## Voice
 
 - **Sentence case**, complete but short sentences.
@@ -87,7 +87,7 @@ The preset sets the voice; these set the floor.
 Compression target: every line earns its label. Cut any line a reader could
 skip without missing the ask.
 
-<!-- part: block:writing-style-structured/review-findings source=mattstack:writing-style-structured version=0.32.32 path=attachments/writing-style/writing-style-structured/review-findings.block.md lines=5-22 -->
+<!-- part: block:writing-style-structured/review-findings source=mattstack:writing-style-structured version=0.32.33 path=attachments/writing-style/writing-style-structured/review-findings.block.md lines=5-22 -->
 ## Review findings
 
 Open with a bolded Conventional Comments label, never a code span, then
@@ -107,13 +107,13 @@ const pageCount = Math.ceil(total / pageSize);
 Use only the lines that carry something: a `nitpick` is the label and one
 line. A process ask is one line.
 
-<!-- part: block:writing-style-structured/review-summary source=mattstack:writing-style-structured version=0.32.32 path=attachments/writing-style/writing-style-structured/review-summary.block.md lines=5-8 -->
+<!-- part: block:writing-style-structured/review-summary source=mattstack:writing-style-structured version=0.32.33 path=attachments/writing-style/writing-style-structured/review-summary.block.md lines=5-8 -->
 ## Review summary
 
 One line: `No blockers. Inline notes on paging and tests.` Only a blocker
 joins it: `One blocker inline (page count).`
 
-<!-- part: block:writing-style-structured/replies-on-your-own-pr source=mattstack:writing-style-structured version=0.32.32 path=attachments/writing-style/writing-style-structured/replies-on-your-own-pr.block.md lines=6-12 -->
+<!-- part: block:writing-style-structured/replies-on-your-own-pr source=mattstack:writing-style-structured version=0.32.33 path=attachments/writing-style/writing-style-structured/replies-on-your-own-pr.block.md lines=6-12 -->
 ## Replies on your own PR
 
 One or two sentences, plain and direct. No thanks opener. State the outcome
@@ -122,12 +122,12 @@ first.
 - `Changed to Record<Status, string>.`
 - `Skipping the lock: the job runs on one worker, and a lock adds a round trip per write.`
 
-<!-- part: block:writing-style-structured/pr-descriptions source=mattstack:writing-style-structured version=0.32.32 path=attachments/writing-style/writing-style-structured/pr-descriptions.block.md lines=6-8 -->
+<!-- part: block:writing-style-structured/pr-descriptions source=mattstack:writing-style-structured version=0.32.33 path=attachments/writing-style/writing-style-structured/pr-descriptions.block.md lines=6-8 -->
 ## PR descriptions
 
 Read `@writing-style-structured/pr-description.md` before drafting.
 
-<!-- part: block:writing-style-structured/commit-messages source=mattstack:writing-style-structured version=0.32.32 path=attachments/writing-style/writing-style-structured/commit-messages.block.md lines=5-9 -->
+<!-- part: block:writing-style-structured/commit-messages source=mattstack:writing-style-structured version=0.32.33 path=attachments/writing-style/writing-style-structured/commit-messages.block.md lines=5-9 -->
 ## Commit messages
 
 - Subject: imperative, sentence case, under 72 characters, with the ticket
diff --git a/plugins/mattstack/skills/writing-style-structured/compiled.json b/plugins/mattstack/skills/writing-style-structured/compiled.json
index 3c521b41b2..3eb3da344a 100644
--- a/plugins/mattstack/skills/writing-style-structured/compiled.json
+++ b/plugins/mattstack/skills/writing-style-structured/compiled.json
@@ -1,8 +1,8 @@
 {
-  "id": "mattstack@0.32.32:writing-style-structured",
+  "id": "mattstack@0.32.33:writing-style-structured",
   "dir": "skills/writing-style-structured",
   "covers": [
-    "mattstack@0.32.32:writing-style-structured"
+    "mattstack@0.32.33:writing-style-structured"
   ],
   "keys": {
     "writing-style-structured/pr-description.md": "skills/writing-style-structured/pr-description.md"