Skip to content

docs: update CLAUDE.md for 2.1.80 migration - #183

Merged
ANcpLua merged 1 commit into
mainfrom
docs/claude-md-2.1.80
Mar 19, 2026
Merged

ANcpLua merged 1 commit into
mainfrom
docs/claude-md-2.1.80

Conversation

@ANcpLua

@ANcpLua ANcpLua commented Mar 19, 2026

Copy link
Copy Markdown
Owner

Syncs CLAUDE.md with changes from this session:

  • marketplace.json version sync enforcement
  • review-fix loop description
  • Codex added to Tri-AI table
  • auto-merge tiers updated
  • effort frontmatter guidance
  • GitGuardian as only required check

Copilot AI review requested due to automatic review settings March 19, 2026 23:35
@ANcpLua
ANcpLua merged commit 8588238 into main Mar 19, 2026
10 of 11 checks passed
@ANcpLua
ANcpLua deleted the docs/claude-md-2.1.80 branch March 19, 2026 23:35
@gemini-code-assist

Copy link
Copy Markdown

Summary of Changes

Hello, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request updates the CLAUDE.md documentation to reflect recent changes and enhancements in the system's operation. The updates cover various aspects, including stricter plugin versioning, expanded roles for AI agents, refined auto-merge processes, and new guidelines for skill development. The goal is to provide a more accurate and comprehensive guide for developers interacting with the Tri-AI system and its workflows.

Highlights

  • Plugin Versioning: Enforced synchronization between plugin.json and marketplace.json versions, with weave-validate.sh failing on mismatches.
  • CI Agent Role Clarification: Updated the description of the CI Agent to explicitly mention its role in pushing direct fix commits and approving clean PRs, detailing the 'review-fix loop'.
  • Tri-AI System Expansion: Introduced 'Codex' as a new AI agent in the Tri-AI system table, detailing its review and auto-merge capabilities.
  • Auto-Merge Tiers Update: Revised the auto-merge tiers to reflect new configurations, including AI agent branches and specific approvals from CodeRabbit, Claude, and Codex.
  • Effort Frontmatter Guidance: Added guidance for effort: low|medium|high frontmatter for skills and commands, linking it to cognitive load.
  • Required Checks: Clarified that GitGuardian is the only required check, with all AI reviews being advisory.
Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature Command Description
Code Review /gemini review Performs a code review for the current pull request in its current state.
Pull Request Summary /gemini summary Provides a summary of the current pull request in its current state.
Comment @gemini-code-assist Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help /gemini help Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for GitHub and other Google products, sign up here.

Footnotes

  1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution.

@coderabbitai

coderabbitai Bot commented Mar 19, 2026

Copy link
Copy Markdown
Contributor

Caution

Review failed

The pull request is closed.

ℹ️ Recent review info
⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: ASSERTIVE

Plan: Pro

Run ID: c3b992af-e32c-4567-92b3-3ca5d18fbf4e

📥 Commits

Reviewing files that changed from the base of the PR and between effc23a and cd07285.

📒 Files selected for processing (1)
  • CLAUDE.md

Cache: Disabled due to data retention organization setting

Knowledge base: Disabled due to data retention organization setting


Summary by CodeRabbit

Release Notes

  • Documentation

    • Updated plugin versioning requirements and marketplace synchronization procedures.
    • Revised CI review and approval workflows with improved automation coordination.
  • New Features

    • Added effort level indicators (low, medium, high) for skills and commands, enabling better resource planning and task orchestration.

Walkthrough

CLAUDE.md updated with revised plugin version synchronization requirements, CI agent workflow behavior, expanded auto-merge tiers for AI agents, coordination/merge policies, CODEOWNERS automation, and new frontmatter capability for skill effort levels.

Changes

Cohort / File(s) Summary
Documentation & Policy Updates
CLAUDE.md
Plugin change mandate now requires syncing both plugin.json and marketplace.json with hard-fail version validation; CI agent workflow changed to review-fix-push loop with approval capability; auto-merge tiers expanded to include Yes for Claude/CodeRabbit/Codex; coordination policy text updated with auto-merge references and GitGuardian as only required check; CODEOWNERS now auto-requests anthropic-code-agent; added codex-code-review.yml workflow and new skill frontmatter effort levels (low|medium|high).

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

Suggested labels

area:docs

📝 Coding Plan
  • Generate coding plan for human review comments

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

@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 updates the CLAUDE.md documentation to align with recent process changes. The updates include enforcing marketplace version synchronization, describing the new review-fix loop, adding Codex to the AI review team, and clarifying auto-merge tiers. The changes are clear and improve the documentation, but I found one minor inconsistency that was introduced.

Comment thread CLAUDE.md
| Copilot | Yes | Yes (Coding Agent) | No |
| CodeRabbit | Yes | No | No |
| CodeRabbit | Yes | No | Yes (tier 3a) |
| Codex | Yes | No | Yes (tier 3c) |

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

medium

With the addition of the Codex agent to the table, the introductory sentence for this section on line 25 is now inaccurate. It states there are three AIs, but the table now lists four. Please update the sentence to reflect that there are four AIs.

Copilot AI 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.

Pull request overview

Updates CLAUDE.md to reflect the repository’s current automation and process expectations during the 2.1.80 migration period, including version-sync enforcement and AI review/auto-merge behavior.

Changes:

  • Documented hard-fail enforcement for plugin version parity between .claude-plugin/marketplace.json and each plugin’s .claude-plugin/plugin.json.
  • Expanded the CI agent description and clarified the “review-fix loop” workflow behavior.
  • Updated Tri-AI/automation sections to include Codex and revised auto-merge tier descriptions; added effort: frontmatter guidance.

Comment thread CLAUDE.md
Comment on lines 23 to 26
@@ -25,14 +26,17 @@ Three autonomous AIs review every PR independently: Claude, Copilot, CodeRabbit.

Copilot AI Mar 19, 2026

Copy link

Choose a reason for hiding this comment

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

The section title/sentence still says "Tri-AI" / "Three autonomous AIs" but the table now includes Codex as a 4th reviewer. Update the wording (and potentially the heading) so it matches the current set of agents listed below.

Copilot uses AI. Check for mistakes.
Comment thread CLAUDE.md

Auto-merge tiers: Dependabot patch/minor -> Copilot fix+CI -> Claude fix+CI+1 approval -> human review.
Auto-merge tiers (see `auto-merge.yml`): Dependabot/Renovate patch+minor → AI agent branches (copilot/, claude/) → CodeRabbit/Claude/Codex approved.
Only required check: GitGuardian. All AI reviews are advisory.

Copilot AI Mar 19, 2026

Copy link

Choose a reason for hiding this comment

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

"Only required check: GitGuardian" appears to be unsupported by the repo configuration: there are no references to GitGuardian anywhere else in the repository, and CI defines multiple checks (JSON/plugin validation, ShellCheck, Markdownlint, actionlint). Consider rephrasing to avoid implying CI failures can be ignored (e.g., distinguish branch-protection required checks vs. expected CI status checks).

Suggested change
Only required check: GitGuardian. All AI reviews are advisory.
Branch protection may enforce specific required status checks (see repository settings). All CI checks (see `.github/workflows/ci.yml`) must pass; AI reviews are advisory.

Copilot uses AI. Check for mistakes.
Comment thread CLAUDE.md
<changelog-mandate>
Update CHANGELOG.md under `## [Unreleased]` before committing. No exceptions.
When modifying a plugin, bump `plugins/<name>/.claude-plugin/plugin.json` version.
When modifying a plugin, bump `plugins/<name>/.claude-plugin/plugin.json` version AND sync marketplace.json.

Copilot AI Mar 19, 2026

Copy link

Choose a reason for hiding this comment

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

In the changelog mandate, "sync marketplace.json" is a bit ambiguous—this repo’s manifest lives at .claude-plugin/marketplace.json (as referenced by weave-validate.sh). Consider using the full path here to reduce the chance of syncing the wrong file.

Suggested change
When modifying a plugin, bump `plugins/<name>/.claude-plugin/plugin.json` version AND sync marketplace.json.
When modifying a plugin, bump `plugins/<name>/.claude-plugin/plugin.json` version AND sync `.claude-plugin/marketplace.json`.

Copilot uses AI. Check for mistakes.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants