Skip to content

docs: working methodology + changelog policy; add AGENTS.md mirror#53

Merged
stephane-segning merged 1 commit into
mainfrom
claude/methodology-docs
Jun 14, 2026
Merged

docs: working methodology + changelog policy; add AGENTS.md mirror#53
stephane-segning merged 1 commit into
mainfrom
claude/methodology-docs

Conversation

@stephane-segning

Copy link
Copy Markdown
Contributor

What

Documents how we actually work in this repo, and adds an AGENTS.md mirror so non-Claude agents get the same guidance.

Why

Our collaboration rhythm (squash-merge, document-with-code, changelog-per-bump, workflow-driven publish, no tags) lived only in conversation and memory. Writing it into CLAUDE.md makes it durable across sessions and tools.

Changes

CLAUDE.md

  • New "Working methodology" section:
    • Implement + document together; one PR per concern.
    • Branch → run the pre-push gate → PR → always squash-merge (gh pr merge <n> --squash --admin).
    • Merge and publish only when explicitly asked.
    • Publish = gh workflow run publish.yml -f dry_run=false; never create a GitHub Release or git tag.
    • One version line; bump PR also updates the changelog.
  • Releasing section: version line bumped to 0.8.0, publish described as workflow-driven (not local npm publish), and a new "Changelog" subsection — one consolidated CHANGELOG.md entry per version (Keep a Changelog), updated in the same PR as the bump, attributed by chore(release) commit boundaries.

AGENTS.md (new)

  • A mirror of CLAUDE.md for any AI agent (Cursor, Codex, Cline, …). Bodies are byte-identical below the header; both files note the sync expectation (edit one, copy across in the same PR).

Notes for reviewers

  • Docs-only. AGENTS.md is a deliberate copy rather than a pointer, per request — the two are kept in sync by hand, and each flags that.

🤖 Generated with Claude Code

Capture how we actually collaborate in this repo so it survives across
sessions and agents:

- New "Working methodology" section in CLAUDE.md: implement+document
  together (one PR per concern), branch → PR → always squash-merge
  (--squash --admin), merge/publish only when explicitly asked, publish
  via `gh workflow run publish.yml -f dry_run=false`, never create a
  GitHub Release or git tag.
- Releasing section: bump the version line to 0.8.0, describe the
  workflow-driven publish, and add a "Changelog" subsection — one
  consolidated CHANGELOG.md entry per version (Keep a Changelog),
  updated in the same PR as the bump.
- Add AGENTS.md as a mirror of CLAUDE.md for non-Claude agents; both
  files note the sync expectation.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@chatgpt-codex-connector

Copy link
Copy Markdown

You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard.

@gemini-code-assist gemini-code-assist Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request introduces a new AGENTS.md file to guide AI coding agents, mirroring the repository's CLAUDE.md file. It also updates CLAUDE.md to keep it in sync, adding a new 'Working methodology' section, updating the 'Releasing' guidelines to reflect version 0.8.0 and the use of the publish.yml workflow, and adding a 'Changelog' section. There are no review comments, and I have no feedback to provide.

Important

The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.

@stephane-segning stephane-segning merged commit 930daf0 into main Jun 14, 2026
3 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant