copy: launch-prep cascade — contributors, origin, stale token + test counts#83
Merged
Conversation
…counts
External-review pass before broad launch. Three categories:
1. Stale "~70-80% reduction" claims in docs/quickstart.mdx:116,
docs/cli/build.mdx:155, docs/COMMANDS.md:28 updated to match the
measured-honesty framing already in cost-benchmark.mdx, low-token-mode.mdx
and the README: ~30% measured ($7.75 vs ~$11 on MNIST), 50-60% targeted
with Haiku routing + per-phase trims (pending second bench), 70-80% on
the roadmap via SDK refactor. The session-025 honesty cascade missed
these three surfaces.
2. Stale test counts: docs/installation.mdx:130 (675 → 743), README.md
tests badge + line 508 (735 → 743). Verified via `pytest -q`:
743 passed, 7 skipped.
3. Website origin story at website/src/pages/index.html:951 stripped of
industry detail ("high-stakes client / power plant" → "eight-week
production ML project"). The prior phrasing brushed the public-repo
confidentiality rules in CLAUDE.md; safer to drop the domain entirely
before broader launch.
Also: footer heading website/src/pages/index.html:1046
"The people behind it." → "Contributors." per user direction.
Memory updated per auto-protocol (session 029 hand-off in STATE.md +
new DECISION_LOG entry). validate-docs 9/11 (0 failures; 2 pre-existing
warnings).
Not in this PR (live on the repo via `gh`): description, homepage, 9
topics, Discussions enabled, 3 seed threads posted (#80 / #81 / #82).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Deploying zero-operators with
|
| Latest commit: |
db54027
|
| Status: | ✅ Deploy successful! |
| Preview URL: | https://071481f6.zero-operators.pages.dev |
| Branch Preview URL: | https://claude-launch-prep-cascade.zero-operators.pages.dev |
|
Preview deployment for your docs. Learn more about Mintlify Previews.
💡 Tip: Enable Workflows to automatically generate PRs for you. |
The prior phrasing forward-referenced "six phases" but those don't
appear until §07 (after Idea, Handoff, and Team sections), and the
§03 lede only enumerates five items, so the framing was both unearned
and self-inconsistent. New headline preserves the compression punch
without promising structure §03 doesn't show.
Aligns with the existing lanes-pretitle on the same section
("5 working days · compressed from 10 weeks").
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Follow-on to db7d680 — the §03 rewrite was missed in the original launch-prep DECISION_LOG entry because it was caught after the initial commit landed. Adds it inline to the cascade-scope list so the audit trail matches the actual file set in the PR. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Pre-launch external-review pass closing three categories of stale or risky public surface area.
~70-80%token claims patched indocs/quickstart.mdx:116,docs/cli/build.mdx:155,docs/COMMANDS.md:28to match the measured-honesty framing already indocs/reference/cost-benchmark.mdx,docs/concepts/low-token-mode.mdx, and the README: ~30% measured ($7.75 vs ~$11 on MNIST), 50-60% targeted (pending second bench), 70-80% on the roadmap via SDK refactor. Session 025's honesty cascade caught the high-traffic surfaces but missed these three.pytest -qoutput (743 passed, 7 skipped):docs/installation.mdx:130(675 → 743),README.mdtests badge + status line (735 → 743).website/src/pages/index.html:951stripped of industry detail. The prior phrasing ("high-stakes client / power plant") brushed against the public-repo confidentiality rules inCLAUDE.md. Replaced with neutral "eight-week production ML project" framing.website/src/pages/index.html:1046"The people behind it." → "Contributors." per user direction.STATE.md, full decision record + alternatives + rationale appended toDECISION_LOG.md.Not in this PR (live on the repo via
gh)https://zerooperators.com, 9 topics applied (ai-agents,claude-code,machine-learning,mlops,autonomous-agents,agent-orchestration,research-engineering,pytorch,devtools).Test plan
pytest -q→ 743 passed, 7 skipped (matches updated docs)scripts/validate-docs.sh→ 9 passed, 0 failed, 2 pre-existing warnings (test-badge grep undercount; client-blocklist skip — both noted in prior STATE entries)docs/quickstart.mdx,docs/cli/build.mdx,docs/COMMANDS.md)743 passingon a hard refresh🤖 Generated with Claude Code