chore: make AGENTS.md canonical, point CLAUDE.md at it with @AGENTS.md#4142
Conversation
|
WalkthroughThis PR restructures repository agent guidance: CLAUDE.md is reduced to a single Changes
Sequence Diagram(s)Not applicable — this PR consists of documentation and workflow configuration changes only. Related Issues: Not specified in provided context. Related PRs: Not specified in provided context. Suggested labels: documentation, ci Suggested reviewers: Not specified in provided context. Poem 🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✨ Finishing Touches📝 Generate docstrings
🧪 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 |
![devin-ai-integration[bot]](https://avatars.githubusercontent.com/in/811515?s=60&v=4){kind=small}
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Nitpick comments (1)
AGENTS.md (1)
45-52: 📐 Maintainability & Code Quality | 🔵 Trivial | ⚡ Quick winKeep the testing guidance root-relative and scoped.
cd internal-packages/run-enginecontradicts the repo-wide “run commands from root withpnpm run” convention, and “Never mock anything” is too absolute for pure unit tests. Keep the examples rooted at the monorepo root and scope testcontainers guidance to the Redis/PostgreSQL integration cases.Source: Learnings
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository UI
Review profile: CHILL
Plan: Pro
Run ID: 289110b6-20db-4a7e-9cdd-e3d07d1e9368
📒 Files selected for processing (3)
.github/workflows/claude-md-audit.ymlAGENTS.mdCLAUDE.md
📜 Review details
⚠️ CI failures not shown inline (4)
GitHub Actions: 📝 Agent Instructions Audit / audit: chore: make AGENTS.md canonical, point CLAUDE.md at it with @AGENTS.md
Conclusion: failure
##[group]Run anthropics/claude-code-action@428971d2ecd6e3a7cb0ee0da2a3a8b33fdb3678d
with:
anthropic_***REDACTED***
use_sticky_comment: true
allowed_bots: devin-ai-integration[bot]
claude_args: --max-turns 25
--model claude-opus-4-8
--allowedTools "Read,Glob,Grep,Bash(git diff:*)"
prompt: You are reviewing a PR to check whether any agent instruction files need updating.
In this repo:
- Root shared agent guidance lives in `AGENTS.md`.
- Root `CLAUDE.md` is only a Claude Code adapter that imports `AGENTS.md`.
- Subdirectories may still have scoped `CLAUDE.md` files.
- `.claude/rules/` contains additional Claude Code guidance.
## Your task
1. Run `git diff origin/main...HEAD --name-only` to see which files changed in this PR.
2. For each changed directory, check the applicable instruction files: root `AGENTS.md`, any `CLAUDE.md` in that directory or a parent directory, and relevant `.claude/rules/` files.
3. Determine if any instruction file should be updated based on the changes. Consider:
- New files/directories that aren't covered by existing documentation
- Changed architecture or patterns that contradict current agent guidance
- New dependencies, services, or infrastructure that agents should know about
- Renamed or moved files that are referenced in an instruction file
- Changes to build commands, test patterns, or development workflows
## Response format
If NO updates are needed, respond with exactly:
✅ Agent instruction files look current for this PR.
If updates ARE needed, respond with a short list:
📝 **Agent instruction updates suggested:**
- `AGENTS.md`: [what should be added/changed]
- `path/to/CLAUDE.md`: [what should be added/changed]
- `.claude/rules/file.md`: [what should be added/changed]
Keep suggestions specific and brief. Only flag things that would actually mislead agents in future sessions.
Do NOT suggest updates for trivial changes (bug fixes, small refactors within existing patterns).
Do NOT suggest creating new...
GitHub Actions: 📝 Agent Instructions Audit / 0_audit.txt: chore: make AGENTS.md canonical, point CLAUDE.md at it with @AGENTS.md
Conclusion: failure
gger.dev/yalt@3.0.0-beta.18
* [new tag] `@trigger.dev/yalt`@3.0.0-beta.19 -> `@trigger.dev/yalt`@3.0.0-beta.19
* [new tag] `@trigger.dev/yalt`@3.0.0-beta.2 -> `@trigger.dev/yalt`@3.0.0-beta.2
* [new tag] `@trigger.dev/yalt`@3.0.0-beta.20 -> `@trigger.dev/yalt`@3.0.0-beta.20
* [new tag] `@trigger.dev/yalt`@3.0.0-beta.21 -> `@trigger.dev/yalt`@3.0.0-beta.21
* [new tag] `@trigger.dev/yalt`@3.0.0-beta.22 -> `@trigger.dev/yalt`@3.0.0-beta.22
* [new tag] `@trigger.dev/yalt`@3.0.0-beta.23 -> `@trigger.dev/yalt`@3.0.0-beta.23
* [new tag] `@trigger.dev/yalt`@3.0.0-beta.24 -> `@trigger.dev/yalt`@3.0.0-beta.24
* [new tag] `@trigger.dev/yalt`@3.0.0-beta.25 -> `@trigger.dev/yalt`@3.0.0-beta.25
* [new tag] `@trigger.dev/yalt`@3.0.0-beta.26 -> `@trigger.dev/yalt`@3.0.0-beta.26
* [new tag] `@trigger.dev/yalt`@3.0.0-beta.27 -> `@trigger.dev/yalt`@3.0.0-beta.27
* [new tag] `@trigger.dev/yalt`@3.0.0-beta.28 -> `@trigger.dev/yalt`@3.0.0-beta.28
* [new tag] `@trigger.dev/yalt`@3.0.0-beta.29 -> `@trigger.dev/yalt`@3.0.0-beta.29
* [new tag] `@trigger.dev/yalt`@3.0.0-beta.3 -> `@trigger.dev/yalt`@3.0.0-beta.3
* [new tag] `@trigger.dev/yalt`@3.0.0-beta.30 -> `@trigger.dev/yalt`@3.0.0-beta.30
* [new tag] `@trigger.dev/yalt`@3.0.0-beta.31 -> `@trigger.dev/yalt`@3.0.0-beta.31
* [new tag] `@trigger.dev/yalt`@3.0.0-beta.32 -> `@trigger.dev/yalt`@3.0.0-beta.32
* [new tag] `@trigger.dev/yalt`@3.0.0-beta.33 -> `@trigger.dev/yalt`@3.0.0-beta.33
* [new tag] `@trigger.dev/yalt`@3.0.0-beta.34 -> `@trigger.dev/yalt`@3.0.0-beta.34
* [new tag] `@trigger.dev/yalt`@3.0.0-beta.35 -> `@trigger.dev/yalt`@3.0.0-beta.35
* [new tag] `@trigger.dev/yalt`@3.0.0-beta.36 -> `@trigger.dev/yalt`@3.0.0-beta.36
* [new tag] `@trigger.dev/yalt`@3.0.0-beta.37 -> `@trigger.dev/yalt`@3.0.0-beta.37
* [new tag] ...
GitHub Actions: 🔎 REVIEW.md Drift Audit / audit: chore: make AGENTS.md canonical, point CLAUDE.md at it with @AGENTS.md
Conclusion: failure
##[group]Run anthropics/claude-code-action@428971d2ecd6e3a7cb0ee0da2a3a8b33fdb3678d
with:
anthropic_***REDACTED***
use_sticky_comment: true
allowed_bots: devin-ai-integration[bot]
claude_args: --max-turns 30
--allowedTools "Read,Glob,Grep,Bash(git diff:*)"
prompt: You are auditing this PR for drift against `.claude/REVIEW.md`.
## Context
`.claude/REVIEW.md` is the repo's source of truth for what AI / agent code reviewers should treat as critical findings (rolling-deploy safety, hot-table indexes, recovery-path queries, testcontainers usage, Lua versioning, etc.). It is consumed by review agents to calibrate severity. If REVIEW.md goes stale, every future agent review degrades.
## Strategy — read this first
You have a hard turn budget. Spend it on signal, not coverage. The audit is allowed to miss things; it is NOT allowed to time out.
1. Read `.claude/REVIEW.md` once, in full.
2. Run `git diff origin/main...HEAD --name-only` to get the list of changed files. Do NOT read the diff content yet.
3. Scan the file-list for relevance to REVIEW.md scope. Relevance signals: changes to Prisma schema, Redis / queue / Lua code, hot tables, recovery / restart loops, new packages, deletions of paths REVIEW.md cites. Skim everything else.
4. Open at most **5 files** total — only the ones most likely to surface a real signal. If nothing in the file-list looks relevant to any REVIEW.md rule, do NOT read any files; go straight to the verdict.
5. Form a verdict and stop. Do not exhaust the turn budget exploring.
Large PRs (>50 files changed) are a strong signal to be MORE selective, not more thorough. Pick 3-5 files at most.
## What to look for
- **Stale references** — does any REVIEW.md rule cite a file, directory, function, table, Prisma model, or package name that has been removed or renamed in this PR (or is already gone from `main`)?
- **Contradictions** — does code in this PR clearly violate a current REVIEW.md rule? (Don't re-review the PR. Only flag if REVIE...
GitHub Actions: 🔎 REVIEW.md Drift Audit / 0_audit.txt: chore: make AGENTS.md canonical, point CLAUDE.md at it with @AGENTS.md
Conclusion: failure
* [new tag] build-metadata-upgrade-logging.rc1 -> build-metadata-upgrade-logging.rc1
* [new tag] build-metadata-upgrade-logging.rc2 -> build-metadata-upgrade-logging.rc2
* [new tag] build-metadata-upgrade-logging.rc3 -> build-metadata-upgrade-logging.rc3
* [new tag] build-new-build-system.rc.1 -> build-new-build-system.rc.1
* [new tag] build-otel-upgrade-rc.0 -> build-otel-upgrade-rc.0
* [new tag] build-otel-upgrade-rc.1 -> build-otel-upgrade-rc.1
* [new tag] build-pre-pull-deployments-rc.1 -> build-pre-pull-deployments-rc.1
* [new tag] build-prod-rescue-rc.1 -> build-prod-rescue-rc.1
* [new tag] build-rate-limiter-fix-rc.1 -> build-rate-limiter-fix-rc.1
* [new tag] build-re2.rc0 -> build-re2.rc0
* [new tag] build-realtime-v2-stream-fix -> build-realtime-v2-stream-fix
* [new tag] build-realtime-v2-stream-fix-2 -> build-realtime-v2-stream-fix-2
* [new tag] build-realtime-v2-stream-fix-3 -> build-realtime-v2-stream-fix-3
* [new tag] build-realtime-v2-stream-fix-4 -> build-realtime-v2-stream-fix-4
* [new tag] build-realtime-v2-stream-fix-5 -> build-realtime-v2-stream-fix-5
* [new tag] build-realtimestreams-dedupe -> build-realtimestreams-dedupe
* [new tag] build-registry-maintenance-rc.1 -> build-registry-maintenance-rc.1
* [new tag] build-registry-maintenance-rc.2 -> build-registry-maintenance-rc.2
* [new tag] build-remote-ecr-rc.0 -> build-remote-ecr-rc.0
* [new tag] build-reschedule-hotfix.rc1 -> build-reschedule-hotfix.rc1
* [new tag] build-resume-fixes.rc1 -> build-resume-fixes.rc1
* [new tag] build-resume-fixes.rc2 -> build-resume-fixes.rc2
* [new tag] build-resume-fixes.rc3 -> build-resume-fixes.r...
🧰 Additional context used
🧠 Learnings (1)
📓 Common learnings
Learnt from: CR
Repo: triggerdotdev/trigger.dev
Timestamp: 2026-07-03T13:02:14.972Z
Learning: Run repository commands from the monorepo root using `pnpm run`.
Learnt from: CR
Repo: triggerdotdev/trigger.dev
Timestamp: 2026-07-03T13:02:14.972Z
Learning: When adding dependencies, edit `package.json` directly instead of using `pnpm add`, then run `pnpm i` from the repo root.
🪛 LanguageTool
AGENTS.md
[style] ~3-~3: Consider a different adjective to strengthen your wording.
Context: ...y. Subdirectory CLAUDE.md files provide deeper context when you navigate into specific...
(DEEP_PROFOUND)
[style] ~109-~109: ‘exact same’ might be wordy. Consider a shorter alternative.
Context: ...to a new or existing package, use the exact same version as the rest of the repo - nev...
(EN_WORDINESS_PREMIUM_EXACT_SAME)
🪛 markdownlint-cli2 (0.22.1)
AGENTS.md
[warning] 212-212: Fenced code blocks should have a language specified
(MD040, fenced-code-language)
🔇 Additional comments (2)
CLAUDE.md (1)
1-1: LGTM!AGENTS.md (1)
56-70: 🎯 Functional CorrectnessVerify
containerTestexists.The provided repo context only shows
redisTestandpostgresTestexports. If@internal/testcontainersdoesn’t actually exportcontainerTest, this example will mislead agents.
2 participants
Tested to confirm that Claude Code picks up the
@AGENTS.mdautomatically with no agent turns.