Skip to content

chore: sync AI tooling and AGENTS.md with 5chan#814

Merged
tomcasaburi merged 1 commit intomasterfrom
codex/chore/ai-tooling-sync
Apr 27, 2026
Merged

chore: sync AI tooling and AGENTS.md with 5chan#814
tomcasaburi merged 1 commit intomasterfrom
codex/chore/ai-tooling-sync

Conversation

@tomcasaburi
Copy link
Copy Markdown
Member

@tomcasaburi tomcasaburi commented Apr 27, 2026 •
edited by cursor Bot
Loading

Summary

  • Port the `release-description` skill across `.claude/`, `.cursor/`, `.codex/`.
  • Align 11 skills, 5 agents, and 3 playbooks with seedit terminology (community, not directory/board) and recent 5chan improvements (skill prompts, examples, URLs, agent subagent_type wiring).
  • Add a Claude `session-start.sh` hook + `hooks.json` entry.
  • Add AGENTS.md rules picked up from 5chan:
    • Review React UI diffs with `vercel-react-best-practices` (and `vercel:react-best-practices` in Codex/Vercel-plugin sessions).
    • Open PRs as ready for review, not draft (so review bots actually run).
    • Do not configure `.claude` agents to use `composer-2` (Cursor-only).
    • Do not configure `.codex/agents/*.toml` with `gpt-5.3-codex` or `gpt-5.3-codex-spark`; standardize on `gpt-5.4`.
    • Default to fresh isolated playwright-cli session; explicit confirmation required to use the contributor's live browser session.
  • 47 files, +378 / −101. No `src/` changes.

Skipped intentionally: 5chan's blotter system (release-notes for end users) — 5chan-specific. The seedit `release` skill stays as-is.

⚠️ Touches AGENTS.md on the "React UI logic changed" task router row — same row that `codex/chore/dev-tooling-doctor-knip` (PR C) extends with `yarn doctor`. A trivial 3-way merge will be needed for whichever PR lands second.

Test plan

  • `corepack yarn install` clean
  • `yarn lint` passes
  • Spot-check a few skill files render correctly in your editor

Note

Low Risk
Low risk: changes are confined to repo automation/docs under .claude/, .cursor/, .codex/, and playbooks, with no runtime src/ logic touched; main risk is workflow friction if hook wiring or URLs/session-mode guidance is incorrect.

Overview
Aligns AI agent/skill guidance across .claude/, .cursor/, and .codex, including updated terminology (community vs. subplebbit/board wording), updated local dev URL usage (http://seedit.localhost:1355), and corrected subagent wiring for tasks like profiling/translation/APK testing.

Adds a Claude sessionStart hook (.claude/hooks/session-start.sh) and wires it in .claude/hooks.json to auto-run corepack yarn install when node_modules is missing.

Updates AGENTS.md and playbooks to require React best-practices review for React UI diffs, enforce fresh Playwright sessions by default (explicit opt-in to attach/reuse a personal browser session), and codify model/PR workflow guardrails (no draft PRs; toolchain-specific model restrictions).

Reviewed by Cursor Bugbot for commit aa8ab27. Bugbot is set up for automated code reviews on this repo. Configure here.

@vercel
Copy link
Copy Markdown

vercel Bot commented Apr 27, 2026 •
edited
Loading

The latest updates on your projects. Learn more about Vercel for GitHub.

Project Deployment Actions Updated (UTC)
seedit Ready Ready Preview, Comment Apr 27, 2026 0:01am

Request Review

@coderabbitai
Copy link
Copy Markdown

coderabbitai Bot commented Apr 27, 2026 •
edited
Loading

Warning

Rate limit exceeded

@tomcasaburi has exceeded the limit for the number of commits that can be reviewed per hour. Please wait 41 minutes and 23 seconds before requesting another review.

To keep reviews running without waiting, you can enable usage-based add-on for your organization. This allows additional reviews beyond the hourly cap. Account admins can enable it under billing.

⌛ How to resolve this issue?

After the wait time has elapsed, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

We recommend that you space out your commits to avoid hitting the rate limit.

🚦 How do rate limits work?

CodeRabbit enforces hourly rate limits for each developer per organization.

Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout.

Please see our FAQ for further information.

ℹ️ Review info
⚙️ Run configuration

Configuration used: defaults

Review profile: CHILL

Plan: Pro

Run ID: 9dcd124d-f3a2-4e9a-97ab-4278eec211af

📥 Commits

Reviewing files that changed from the base of the PR and between 3665384 and aa8ab27.

📒 Files selected for processing (47)
  • .claude/agents/browser-check.md
  • .claude/agents/code-quality.md
  • .claude/agents/profiler.md
  • .claude/agents/react-doctor-fixer.md
  • .claude/agents/react-patterns-enforcer.md
  • .claude/hooks.json
  • .claude/hooks/session-start.sh
  • .claude/skills/deslop/SKILL.md
  • .claude/skills/implement-plan/SKILL.md
  • .claude/skills/inspect-elements/SKILL.md
  • .claude/skills/make-closed-issue/SKILL.md
  • .claude/skills/playwright-cli/SKILL.md
  • .claude/skills/profile-browsing/SKILL.md
  • .claude/skills/refactor-pass/SKILL.md
  • .claude/skills/release-description/SKILL.md
  • .claude/skills/test-apk/SKILL.md
  • .claude/skills/translate/SKILL.md
  • .claude/skills/you-might-not-need-an-effect/SKILL.md
  • .codex/agents/browser-check.toml
  • .codex/skills/deslop/SKILL.md
  • .codex/skills/inspect-elements/SKILL.md
  • .codex/skills/make-closed-issue/SKILL.md
  • .codex/skills/playwright-cli/SKILL.md
  • .codex/skills/profile-browsing/SKILL.md
  • .codex/skills/refactor-pass/SKILL.md
  • .codex/skills/release-description/SKILL.md
  • .codex/skills/you-might-not-need-an-effect/SKILL.md
  • .cursor/agents/browser-check.md
  • .cursor/agents/code-quality.md
  • .cursor/agents/profiler.md
  • .cursor/agents/react-doctor-fixer.md
  • .cursor/agents/react-patterns-enforcer.md
  • .cursor/skills/deslop/SKILL.md
  • .cursor/skills/implement-plan/SKILL.md
  • .cursor/skills/inspect-elements/SKILL.md
  • .cursor/skills/make-closed-issue/SKILL.md
  • .cursor/skills/playwright-cli/SKILL.md
  • .cursor/skills/profile-browsing/SKILL.md
  • .cursor/skills/refactor-pass/SKILL.md
  • .cursor/skills/release-description/SKILL.md
  • .cursor/skills/test-apk/SKILL.md
  • .cursor/skills/translate/SKILL.md
  • .cursor/skills/you-might-not-need-an-effect/SKILL.md
  • AGENTS.md
  • docs/agent-playbooks/hooks-setup.md
  • docs/agent-playbooks/known-surprises.md
  • docs/agent-playbooks/skills-and-tools.md
✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Commit unit tests in branch codex/chore/ai-tooling-sync

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.

❤️ Share

Comment @coderabbitai help to get the list of available commands and usage tips.

@tomcasaburi tomcasaburi mentioned this pull request Apr 27, 2026
Merged
8 tasks
@tomcasaburi
chore: sync AI tooling and AGENTS.md with 5chan
aa8ab27 
Port release-description skill across .claude / .cursor / .codex.
Align playbook content, skills, agents, and hooks with seedit
terminology (community, not directory or board).
Add AGENTS.md rules picked up from 5chan: vercel-react-best-practices
review, ready-for-review PR rule, agent model constraints,
playwright session policy, you-might-not-need-an-effect review.
@tomcasaburi tomcasaburi force-pushed the codex/chore/ai-tooling-sync branch from cc2fb9d to aa8ab27 Compare April 27, 2026 12:01
@tomcasaburi tomcasaburi merged commit f3fb5fd into master Apr 27, 2026
8 checks passed
@tomcasaburi tomcasaburi deleted the codex/chore/ai-tooling-sync branch April 27, 2026 12:28
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

1 participant

@tomcasaburi