docs: add canonical AGENTS.md + CLAUDE.md shim, re-track agent docs, ignore .claude/.agents#13
Conversation
Recreate the root CLAUDE.md (project context for Claude Code) and remove it from
.gitignore so it is committed and shared again; .claude/ stays ignored. The file
captures per-project commands, the four validation gates, and the non-obvious
gotchas surfaced during end-to-end validation (set -e increment footgun,
stderr/stdout JSON discipline, adminer dual-network/loopback, the spamd-is-not-a-
milter trap, php-fpm TCP, init.sql/${MYSQL_DATABASE}, scratch-image healthchecks).
Reviewer's GuideRestores the root CLAUDE.md documentation file to version control and updates .gitignore so that only the .claude/ directory remains ignored, reintroducing a detailed, bilingual project guide for Claude Code while keeping other ignore rules intact. File-Level Changes
Tips and commandsInteracting with Sourcery
Customizing Your ExperienceAccess your dashboard to:
Getting Help
|
|
Warning Review limit reached
More reviews will be available in 23 minutes and 34 seconds. Learn how PR review limits work. Your organization has used up its prepaid credits, and credit purchases are no longer available. Enable the review add-on in the billing tab to keep reviews running — you're only billed for reviews past your plan's rate limits ($0.25/file). ⌛ How to resolve this issue?After more reviews become available, a review can be triggered using the To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based credits. 🚦 How do rate limits work?CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability. For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window. Please see our Fair Usage Limits Policy for further information. ℹ️ Review info⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (3)
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![sourcery-ai[bot]](https://avatars.githubusercontent.com/in/48477?s=60&v=4){kind=small}
There was a problem hiding this comment.
Hey - I've left some high level feedback:
- The hard-coded test counts in the validation section (e.g.,
# 42 tests,# 43 tests) are likely to drift over time; consider either omitting the exact numbers or deriving them programmatically in the test runners and describing them more generically here. - Several details in the Gotchas section (ports, container names, healthcheck behavior, etc.) are tightly coupled to the current compose definitions; it may be worth explicitly noting that CLAUDE.md should be updated alongside any future compose/service changes to avoid this doc becoming misleading.
Prompt for AI Agents
Please address the comments from this code review:
## Overall Comments
- The hard-coded test counts in the validation section (e.g., `# 42 tests`, `# 43 tests`) are likely to drift over time; consider either omitting the exact numbers or deriving them programmatically in the test runners and describing them more generically here.
- Several details in the Gotchas section (ports, container names, healthcheck behavior, etc.) are tightly coupled to the current compose definitions; it may be worth explicitly noting that CLAUDE.md should be updated alongside any future compose/service changes to avoid this doc becoming misleading.Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.
…n shim Track the existing root AGENTS.md as the single source of agent operating rules, and replace CLAUDE.md's duplicated policy with a thin shim that imports it (@AGENTS.md) plus Claude-specific runtime notes. Resolves the single-source-of- truth drift flagged by the maintaining-agent-docs validator (now 0 warnings).
w7-mgfcode
changed the title
2 participants
Summary
Establishes the canonical-source agent-doc model and cleans up assistant-file tracking.
Changes
AGENTS.md— now tracked as the single canonical source of agent operating rules (purpose, build/test commands, code style, architecture notes, validation, security, conventions). Repo-verified; unchanged content.CLAUDE.md— reduced from a 64-line duplicate to an 11-line thin shim that@AGENTS.md-imports the canonical rules and adds only Claude-specific runtime notes. No duplicated policy (single source of truth)..gitignore—CLAUDE.mdremoved from ignore (now tracked);.claude/and.agents/ignored as local-only assistant tooling.Background
CLAUDE.md(and a.claude/tooling dir) were deleted + gitignored in PR #6. This restores shared agent context in the modern AGENTS.md-canonical + provider-shim layout, while keeping machine-local tooling (.claude/,.agents/) out of git.Validation
maintaining-agent-docsvalidator: 0 errors, 0 warnings (1 advisory info).git check-ignore:CLAUDE.md/AGENTS.mdtrackable;.claude/,.agents/ignored.main; CI ShellCheck + Compose Validate required.