no-mistakes(review): Unify generator cost test wording across skills

Assisted-by: no-mistakes:claude:claude-sonnet-5-5

Author: dmealing

CHANGELOG.md

@@ -60,12 +60,13 @@ generator catalog and the Atlas evaluation are 1.2 work.
 
 ### Added
 
-- **Agent skills: a cost test for owned generators.** The `metaobjects-codegen` skill now says when not to write a generator: only when generator plus
-  output is smaller than the hand-written code it replaces (generator code counted as
-  hand-written cost), more instances of the shape are expected, or drift protection is the
+- **Agent skills: a cost test for owned generators.** The `metaobjects-codegen` skill now says when not to write a generator: only when generator code plus
+  its generated output and added metadata is fewer lines than the hand-written code it
+  replaces, more instances of the shape are expected, or drift protection is the
   point; a general-shape generator belongs in the library. The `metaobjects-audit` skill applies
   the same test: a one-off hand-written layer that fails it is reported as acceptable, and any
-  generated-share figure must carry the net hand-written line change and is never a target.
+  generated-share figure must carry the net hand-written line change (a figure to report, not
+  the test) and is never a target.
   Documentation only; no code or generator changed.
 - **TypeScript: the `cube-model` reference generator (FR-044 Plan 4).** `cubeModel()` writes the
   reporting vocabulary as Cube data-model files, `model/cubes/<Cube>.yml`: a cube for each

agent-context/skills/metaobjects-audit/SKILL.md

@@ -8,8 +8,9 @@ description: Use when assessing how well a project has adopted MetaObjects — g
 **Thesis.** Typed metadata is the durable spine; generated code is the disposable
 artifact. Hand-writing a layer the metadata could own creates a second source of
 truth for one fact — it will drift. This audit hunts those second sources of truth
-and proposes folding them into the spine — where doing so costs fewer hand-written lines
-than it saves, more of that shape are coming, or silent drift is the risk. A one-off layer
+and proposes folding them into the spine — where the generator code plus its generated output
+and added metadata is fewer lines than the hand-written code it replaces, more of that shape
+are coming, or silent drift is the risk. A one-off layer
 that fails that cost test is acceptable, not a defect.
 
 **Boundary — read-only.** Deliverables: `.metaobjects/adoption-audit.json` (machine-readable
@@ -51,8 +52,9 @@ Actual cutovers run through the existing skills mapped per finding tier (§ Brid
 Compute **leverage ratio** = `generated_lines / (metadata_lines + generator_lines)`;
 healthy = multi-× (example: ~4.7k spine → ~15.7k generated ≈ 3.3×). **Never report a
 generated-share or leverage figure alone, and never as a target:** pair it with the **net
-hand-written line change** (app lines removed minus generator and metadata lines added;
-generator code is hand-written cost). A share can rise while total hand-written code grows.
+hand-written line change**, a figure to report and not the cost test (hand-written lines
+removed minus generator and metadata lines added). A share can rise while total hand-written
+code grows.
 
 **Coverage matrix:** per entity/projection/value — query helpers? view? routes? UI?
 The gap between "modeled + query helpers" and "has view + route + UI" is the headline

agent-context/skills/metaobjects-codegen/references/owning-generators.md

@@ -55,10 +55,8 @@ written.
 **Is it worth a generator? Run the cost test first.** Write an adopter-owned generator only
 when at least one holds:
 
-1. **It is smaller.** The generator plus its emitted output, plus the metadata it adds, is
-   fewer lines than the hand-written code it replaces. Count generator code as hand-written
-   cost: it is code the team reads, tests and maintains. A generated-line total does not
-   count; the emitted files cost nothing to write but the generator that makes them does.
+1. **It is smaller.** The generator code plus its generated output, plus the metadata it
+   adds, is fewer lines than the hand-written code it replaces.
 2. **More instances are coming.** The app will keep adding entities, routes or events of this
    shape, so the generator's cost is paid back as the model grows.
 3. **Drift protection is the point.** A change to the model could pass the compiler and go

fixtures/agent-context-conformance/java-kotlin-react-tanstack/expected/.claude/skills/metaobjects-audit/SKILL.md

@@ -8,8 +8,9 @@ description: Use when assessing how well a project has adopted MetaObjects — g
 **Thesis.** Typed metadata is the durable spine; generated code is the disposable
 artifact. Hand-writing a layer the metadata could own creates a second source of
 truth for one fact — it will drift. This audit hunts those second sources of truth
-and proposes folding them into the spine — where doing so costs fewer hand-written lines
-than it saves, more of that shape are coming, or silent drift is the risk. A one-off layer
+and proposes folding them into the spine — where the generator code plus its generated output
+and added metadata is fewer lines than the hand-written code it replaces, more of that shape
+are coming, or silent drift is the risk. A one-off layer
 that fails that cost test is acceptable, not a defect.
 
 **Boundary — read-only.** Deliverables: `.metaobjects/adoption-audit.json` (machine-readable
@@ -51,8 +52,9 @@ Actual cutovers run through the existing skills mapped per finding tier (§ Brid
 Compute **leverage ratio** = `generated_lines / (metadata_lines + generator_lines)`;
 healthy = multi-× (example: ~4.7k spine → ~15.7k generated ≈ 3.3×). **Never report a
 generated-share or leverage figure alone, and never as a target:** pair it with the **net
-hand-written line change** (app lines removed minus generator and metadata lines added;
-generator code is hand-written cost). A share can rise while total hand-written code grows.
+hand-written line change**, a figure to report and not the cost test (hand-written lines
+removed minus generator and metadata lines added). A share can rise while total hand-written
+code grows.
 
 **Coverage matrix:** per entity/projection/value — query helpers? view? routes? UI?
 The gap between "modeled + query helpers" and "has view + route + UI" is the headline

fixtures/agent-context-conformance/java-kotlin-react-tanstack/expected/.claude/skills/metaobjects-codegen/references/owning-generators.md

@@ -55,10 +55,8 @@ written.
 **Is it worth a generator? Run the cost test first.** Write an adopter-owned generator only
 when at least one holds:
 
-1. **It is smaller.** The generator plus its emitted output, plus the metadata it adds, is
-   fewer lines than the hand-written code it replaces. Count generator code as hand-written
-   cost: it is code the team reads, tests and maintains. A generated-line total does not
-   count; the emitted files cost nothing to write but the generator that makes them does.
+1. **It is smaller.** The generator code plus its generated output, plus the metadata it
+   adds, is fewer lines than the hand-written code it replaces.
 2. **More instances are coming.** The app will keep adding entities, routes or events of this
    shape, so the generator's cost is paid back as the model grows.
 3. **Drift protection is the point.** A change to the model could pass the compiler and go

fixtures/agent-context-conformance/java-react/expected/.claude/skills/metaobjects-audit/SKILL.md

@@ -8,8 +8,9 @@ description: Use when assessing how well a project has adopted MetaObjects — g
 **Thesis.** Typed metadata is the durable spine; generated code is the disposable
 artifact. Hand-writing a layer the metadata could own creates a second source of
 truth for one fact — it will drift. This audit hunts those second sources of truth
-and proposes folding them into the spine — where doing so costs fewer hand-written lines
-than it saves, more of that shape are coming, or silent drift is the risk. A one-off layer
+and proposes folding them into the spine — where the generator code plus its generated output
+and added metadata is fewer lines than the hand-written code it replaces, more of that shape
+are coming, or silent drift is the risk. A one-off layer
 that fails that cost test is acceptable, not a defect.
 
 **Boundary — read-only.** Deliverables: `.metaobjects/adoption-audit.json` (machine-readable
@@ -51,8 +52,9 @@ Actual cutovers run through the existing skills mapped per finding tier (§ Brid
 Compute **leverage ratio** = `generated_lines / (metadata_lines + generator_lines)`;
 healthy = multi-× (example: ~4.7k spine → ~15.7k generated ≈ 3.3×). **Never report a
 generated-share or leverage figure alone, and never as a target:** pair it with the **net
-hand-written line change** (app lines removed minus generator and metadata lines added;
-generator code is hand-written cost). A share can rise while total hand-written code grows.
+hand-written line change**, a figure to report and not the cost test (hand-written lines
+removed minus generator and metadata lines added). A share can rise while total hand-written
+code grows.
 
 **Coverage matrix:** per entity/projection/value — query helpers? view? routes? UI?
 The gap between "modeled + query helpers" and "has view + route + UI" is the headline

fixtures/agent-context-conformance/java-react/expected/.claude/skills/metaobjects-codegen/references/owning-generators.md

@@ -55,10 +55,8 @@ written.
 **Is it worth a generator? Run the cost test first.** Write an adopter-owned generator only
 when at least one holds:
 
-1. **It is smaller.** The generator plus its emitted output, plus the metadata it adds, is
-   fewer lines than the hand-written code it replaces. Count generator code as hand-written
-   cost: it is code the team reads, tests and maintains. A generated-line total does not
-   count; the emitted files cost nothing to write but the generator that makes them does.
+1. **It is smaller.** The generator code plus its generated output, plus the metadata it
+   adds, is fewer lines than the hand-written code it replaces.
 2. **More instances are coming.** The app will keep adding entities, routes or events of this
    shape, so the generator's cost is paid back as the model grows.
 3. **Drift protection is the point.** A change to the model could pass the compiler and go

fixtures/agent-context-conformance/python/expected/.claude/skills/metaobjects-audit/SKILL.md

@@ -8,8 +8,9 @@ description: Use when assessing how well a project has adopted MetaObjects — g
 **Thesis.** Typed metadata is the durable spine; generated code is the disposable
 artifact. Hand-writing a layer the metadata could own creates a second source of
 truth for one fact — it will drift. This audit hunts those second sources of truth
-and proposes folding them into the spine — where doing so costs fewer hand-written lines
-than it saves, more of that shape are coming, or silent drift is the risk. A one-off layer
+and proposes folding them into the spine — where the generator code plus its generated output
+and added metadata is fewer lines than the hand-written code it replaces, more of that shape
+are coming, or silent drift is the risk. A one-off layer
 that fails that cost test is acceptable, not a defect.
 
 **Boundary — read-only.** Deliverables: `.metaobjects/adoption-audit.json` (machine-readable
@@ -51,8 +52,9 @@ Actual cutovers run through the existing skills mapped per finding tier (§ Brid
 Compute **leverage ratio** = `generated_lines / (metadata_lines + generator_lines)`;
 healthy = multi-× (example: ~4.7k spine → ~15.7k generated ≈ 3.3×). **Never report a
 generated-share or leverage figure alone, and never as a target:** pair it with the **net
-hand-written line change** (app lines removed minus generator and metadata lines added;
-generator code is hand-written cost). A share can rise while total hand-written code grows.
+hand-written line change**, a figure to report and not the cost test (hand-written lines
+removed minus generator and metadata lines added). A share can rise while total hand-written
+code grows.
 
 **Coverage matrix:** per entity/projection/value — query helpers? view? routes? UI?
 The gap between "modeled + query helpers" and "has view + route + UI" is the headline

fixtures/agent-context-conformance/python/expected/.claude/skills/metaobjects-codegen/references/owning-generators.md

@@ -55,10 +55,8 @@ written.
 **Is it worth a generator? Run the cost test first.** Write an adopter-owned generator only
 when at least one holds:
 
-1. **It is smaller.** The generator plus its emitted output, plus the metadata it adds, is
-   fewer lines than the hand-written code it replaces. Count generator code as hand-written
-   cost: it is code the team reads, tests and maintains. A generated-line total does not
-   count; the emitted files cost nothing to write but the generator that makes them does.
+1. **It is smaller.** The generator code plus its generated output, plus the metadata it
+   adds, is fewer lines than the hand-written code it replaces.
 2. **More instances are coming.** The app will keep adding entities, routes or events of this
    shape, so the generator's cost is paid back as the model grows.
 3. **Drift protection is the point.** A change to the model could pass the compiler and go

fixtures/agent-context-conformance/ts-react-tanstack/expected/.claude/skills/metaobjects-audit/SKILL.md

@@ -8,8 +8,9 @@ description: Use when assessing how well a project has adopted MetaObjects — g
 **Thesis.** Typed metadata is the durable spine; generated code is the disposable
 artifact. Hand-writing a layer the metadata could own creates a second source of
 truth for one fact — it will drift. This audit hunts those second sources of truth
-and proposes folding them into the spine — where doing so costs fewer hand-written lines
-than it saves, more of that shape are coming, or silent drift is the risk. A one-off layer
+and proposes folding them into the spine — where the generator code plus its generated output
+and added metadata is fewer lines than the hand-written code it replaces, more of that shape
+are coming, or silent drift is the risk. A one-off layer
 that fails that cost test is acceptable, not a defect.
 
 **Boundary — read-only.** Deliverables: `.metaobjects/adoption-audit.json` (machine-readable
@@ -51,8 +52,9 @@ Actual cutovers run through the existing skills mapped per finding tier (§ Brid
 Compute **leverage ratio** = `generated_lines / (metadata_lines + generator_lines)`;
 healthy = multi-× (example: ~4.7k spine → ~15.7k generated ≈ 3.3×). **Never report a
 generated-share or leverage figure alone, and never as a target:** pair it with the **net
-hand-written line change** (app lines removed minus generator and metadata lines added;
-generator code is hand-written cost). A share can rise while total hand-written code grows.
+hand-written line change**, a figure to report and not the cost test (hand-written lines
+removed minus generator and metadata lines added). A share can rise while total hand-written
+code grows.
 
 **Coverage matrix:** per entity/projection/value — query helpers? view? routes? UI?
 The gap between "modeled + query helpers" and "has view + route + UI" is the headline