codebase-argus skill
✓ VerifiedPerforms evidence-first multi-agent reviews of GitHub pull requests, CI failures, and downstream fork synchronization.
- GitHub stars
- 59
- Files
- 2
- Last commit
- Nov 9, 2026
- License
- MIT
- Allowed tools
- —
What does the codebase-argus skill do?
codebase-argus performs evidence-first multi-agent reviews of GitHub pull requests, CI failures, and downstream fork synchronization.
Summary generated from the skill's SKILL.md.
About the codebase-argus skill
Developers managing complex repositories can use this tool to perform evidence-first reviews of GitHub pull requests, CI failures, and downstream fork synchronizations. It functions as a portable playbook for coding agents, providing a structured way to analyze code changes by gathering concrete evidence like failing checks or dependency updates. The system can be used via a local CLI or deployed as a GitHub App webhook server to automate reviews for specific pull request events.
Users can choose between deterministic rule-based reviews or multi-agent tribunals that compare outputs from different providers like OpenAI, Anthropic, or Gemini. The tool supports analyzing local log files or fetching GitHub Actions logs directly using a GitHub token. It also provides an autofix-plan feature to suggest mechanical repairs for issues like linter errors or lockfile refreshes. For teams maintaining long-lived forks, it offers specialized commands to assess the risks of merging or rebasing against an upstream repository.
What an agent can do with it
- 1Analyze CI failure logsExamine a failing GitHub Actions job log to identify the most likely root cause and a potential fix.
- 2Plan automated code repairsGenerate a plan for narrow mechanical failures such as updating lockfiles or fixing linting issues.
Written from the skill's SKILL.md. Every use case is checked against a quote from it.
How to install the codebase-argus skill
Each command copies the skill folder into the client's skills directory. Restart the client or start a new session to load it.Install the codebase-argus skill in Plugin
/plugin marketplace add AaronZ345/codebase-argus /plugin install codebase-argus@codebase-argus
Install the codebase-argus skill in Claude Code
~/.claude/skills/codebase-argus/SKILL.md
$ npx degit AaronZ345/codebase-argus/skills/codebase-argus ~/.claude/skills/codebase-argusInstall the codebase-argus skill in Claude Code (project)
.claude/skills/codebase-argus/SKILL.md
$ npx degit AaronZ345/codebase-argus/skills/codebase-argus .claude/skills/codebase-argusInstall the codebase-argus skill in Codex
~/.agents/skills/codebase-argus/SKILL.md
$ npx degit AaronZ345/codebase-argus/skills/codebase-argus ~/.agents/skills/codebase-argusInstall the codebase-argus skill in Gemini CLI
~/.gemini/skills/codebase-argus/SKILL.md
$ npx degit AaronZ345/codebase-argus/skills/codebase-argus ~/.gemini/skills/codebase-argusInstall the codebase-argus skill in Claude.ai
npx degit AaronZ345/codebase-argus/skills/codebase-argus codebase-argus && zip -r codebase-argus.zip codebase-argus # claude.ai → Customize → Skills → + → Create skill → Upload a skill → codebase-argus.zip
Automated checks
Ran Nov 14, 2026Full report →Passed our automated checks. That is not a security audit: read the scripts before you let an agent run them. How checks work · What to fix for more points
- Source repository linked and reachableaaronz345/codebase-argus/skills/codebase-argus is public and reachablegithub.com/aaronz345/codebase-argus/tree/HEAD/skills/codebas ↗Pass
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit 2026-11-09github.com/aaronz345/codebase-argus/commits ↗Pass
- No download-and-run or credential theft in scriptsNo scripts in the skill folderPass
- No hidden instructions in SKILL.mdNo override phrases, safeguard switches, credential requests or hidden charactersgithub.com/aaronz345/codebase-argus/blob/HEAD/skills/codebas ↗Pass
- Pre-approved tools are scopedNo pre-approved tools; the agent asks before using onegithub.com/aaronz345/codebase-argus/blob/HEAD/skills/codebas ↗Pass
- SKILL.md follows the Agent Skills formatthe description does not say when to use the skillgithub.com/aaronz345/codebase-argus/blob/HEAD/skills/codebas ↗Finding
SKILL.md
View on GitHubCodebase Argus
Use this portable agent playbook for evidence-first codebase review across GitHub PRs, CI failures, and downstream fork integration work. It works as an OpenClaw/ClawHub skill, Codex project instruction, Claude Code project instruction, or a plain Markdown playbook for any coding agent that can run local shell commands.
Both upstream and downstream workflows can send the same evidence package to one provider or a multi-agent tribunal.
Fast Path
From a Codebase Argus checkout:
npm install
npm run argus -- review owner/repo#123
For private repositories or higher GitHub API limits:
GITHUB_TOKEN=<read-only-token> npm run argus -- review owner/repo#123
Do not print tokens. Do not write tokens to files.
For a read-only GitHub Actions job summary, use the companion Action:
- uses: AaronZ345/codebase-argus-action@v1
with:
pull-request: ${{ github.repository }}#${{ github.event.pull_request.number }}
Upstream PR Review
Default review is deterministic and rule-based:
npm run argus -- review owner/repo#123 --format markdown
Use a policy file when the repository has local rules:
npm run argus -- review owner/repo#123 --policy .codebase-argus.yml
Use API providers when credentials are available in the environment:
OPENAI_API_KEY=<key> npm run argus -- review owner/repo#123 --provider openai-api
ANTHROPIC_API_KEY=<key> npm run argus -- review owner/repo#123 --provider anthropic-api
GEMINI_API_KEY=<key> npm run argus -- review owner/repo#123 --provider gemini-api
Use local CLI providers only in trusted local workspaces:
npm run argus -- review owner/repo#123 --provider codex-cli
npm run argus -- review owner/repo#123 --provider claude-cli
npm run argus -- review owner/repo#123 --provider gemini-cli
For multi-agent review:
npm run argus -- review owner/repo#123 --tribunal openai-api,claude-cli,codex-cli
Treat output as review assistance. Do not approve, merge, push, or post comments automatically unless the user explicitly asks.
CI Failure Review
When the user provides a failing job log or local log file, review it through the same provider system:
npm run argus -- ci-log logs/failure.txt
npm run argus -- ci-log logs/failure.txt --provider codex-cli
npm run argus -- ci-log logs/failure.txt --tribunal codex-cli,claude-cli,gemini-cli
When the user points at a GitHub PR with failing Actions checks, fetch the job logs directly:
GITHUB_TOKEN=<read-only-token> npm run argus -- ci-github owner/repo#123
GITHUB_TOKEN=<read-only-token> npm run argus -- ci-github owner/repo#123 --provider codex-cli
Focus on the first failing command, the most likely root cause, and the smallest fix that can be verified locally.
Autofix Plan
Use autofix-plan when the user asks for suggested fixes, safe automatic repair,
or a branch plan for narrow mechanical failures:
npm run argus -- autofix-plan owner/repo#123
The plan covers gated lanes such as npm lockfile refreshes, snapshot updates, and formatter/linter fixes. Treat it as a command plan; do not execute, push, or open a PR unless the user explicitly asks.
GitHub App Webhook Review
For automatic PR review, the deployed Next.js server exposes:
POST /api/github/webhook
GET /api/github/app-manifest
Required environment:
GITHUB_WEBHOOK_SECRET=<secret>
GITHUB_APP_ID=<app-id>
GITHUB_APP_PRIVATE_KEY=<pem-or-escaped-pem>
Use GITHUB_APP_PRIVATE_KEY_BASE64 if storing multiline PEM is awkward. The
webhook verifies X-Hub-Signature-256, reviews opened, reopened,
ready_for_review, and synchronize, ignores draft PRs, posts COMMENT reviews
only, and can add inline comments when ARGUS_WEBHOOK_INLINE_COMMENTS=true.
Supported PR comment commands:
/argus help
/argus review
/argus ci
/argus autofix
/argus pause
/argus resume
/argus pause applies argus:paused; automatic review skips PRs with that label.
/argus resume removes it.
Do not approve, request changes, merge, push, or post comments outside this configured webhook path unless the user explicitly asks.
What To Look For
Prioritize findings with concrete evidence:
- failing or pending checks;
- source changes without matching tests;
- workflow edits, especially
pull_request_target; - auth, token, webhook, payment, signature, or route-handling changes;
- dependency and lockfile changes;
- large PRs that exceed policy gates;
- stacked PRs targeting non-default base branches;
- merge queue states such as blocked, behind, dirty, or unstable;
- agreement between multiple providers.
Low-confidence model-only claims need manual verification before reporting them as facts.
Downstream Fork Sync And Integration Review
For long-lived fork maintenance, use the downstream CLI first:
npm run argus -- downstream owner/upstream me/fork
npm run argus -- downstream owner/upstream me/fork --upstream-branch main --fork-branch feature/demo
For AI CLI review of merge/rebase risk:
npm run argus -- downstream owner/upstream me/fork --fork-branch feature/demo --provider codex-cli
npm run argus -- downstream owner/upstream me/fork --fork-branch feature/demo --tribunal codex-cli,claude-cli,gemini-cli
When the user explicitly asks the agent to perform the downstream integration,
use sync. It prints a dry-run plan unless --execute is present:
npm run argus -- sync owner/upstream me/fork --mode merge --fork-branch feature/demo --test "npm test"
npm run argus -- sync owner/upstream me/fork --mode rebase --fork-branch feature/demo --test "npm test" --execute --push --create-pr
Execution rules:
- run
downstreamwith a provider or tribunal first for risky branches; - prefer a sync branch such as
sync/upstream-main; - push only with explicit
--push; - open a PR only with explicit
--create-pr; - never push directly over the user's original target branch;
- report failed commands, conflicts, and test output without hiding them.
The downstream prompt must consider both integration paths:
- merge upstream into the fork, using
git merge-treeconflict evidence; - rebase the fork on upstream, using temporary worktree rebase simulation;
- patch-equivalent cleanup candidates from
git cherry -v; - semantic patch movement from
git range-diff; - backup, test, and force-with-lease gates before any push.
Use the local dashboard when a human needs to inspect the same evidence visually:
npm run dev
Open the Downstream Fork Sync, Downstream Merge/Rebase Risk, and Downstream Agent Workflow panels. The local analyzer works in .cache/repos and temporary worktrees, and must not push or force-push by itself. Actual sync execution belongs to the CLI sync command and only runs after explicit flags.
Files in this skill
2codebase-argus skill questions
How do I install the codebase-argus skill in Claude Code?
Run npx degit AaronZ345/codebase-argus/skills/codebase-argus ~/.claude/skills/codebase-argus. Claude Code loads skills from ~/.claude/skills (all projects) or .claude/skills (one project) and uses a skill when its description matches the task.
Which clients can use the codebase-argus skill?
Any client that reads the Agent Skills format: Claude Code, Codex, Gemini CLI and claude.ai (upload as a ZIP). Scripts in the skill run only where the client allows code execution.
How do I review a specific GitHub pull request?
You can use the command npm run argus -- review owner/repo#123 to start a review.
How can I review CI failure logs?
You can provide a local log file using npm run argus -- ci-log logs/failure.txt or fetch logs directly from GitHub using the ci-github command.