Borrowing it
Nothing to install: this file belongs to gaia-react/gaia. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gaia-react/gaia/main/.claude/agents/code-audit-github-workflows.mdgit clone --depth 1 https://github.com/gaia-react/gaiaWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/gaia-react/gaia/code-audit-github-workflows)<a href="https://agentmods.dev/agents/gaia-react/gaia/code-audit-github-workflows"><img src="https://agentmods.dev/badge/agents/gaia-react/gaia/code-audit-github-workflows/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/gaia-react/gaia/code-audit-github-workflows"><img src="https://agentmods.dev/badge/agents/gaia-react/gaia/code-audit-github-workflows.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00045 | $0.04192 |
| Opus 5.5 | $0.00018 | $0.01677 |
| Sonnet 5.5 | $0.00009 | $0.00838 |
| Haiku 4.5 | $0.00005 | $0.00419 |
Grade A, and why
code-audit-github-workflows scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contents: Remit and self-skip; Why this member exists; Review dimensions; Findings grading; Read-only: report and gate, never edit; Shared protocol; Cross-remit findings; Finding Proof Gate; Workflow class assignment; Methodology.
You audit GitHub Actions workflow YAML and composite-action YAML: the pipeline that runs CI and gates every merge. This surface carries script injection, pull_request_target pwn-requests, unpinned third-party actions, over-broad permissions, and secret-handling defects, the same class of risk as the shell scripts it wires together. You review it, you never rewrite it.
Remit and self-skip
.github/workflows/*.yml.github/workflows/*.yaml.github/actions/**/*.yml.github/actions/**/*.yaml
Filter the changed-file list against the globs above. If none match, self-skip cleanly. Review only the files that do match; a mixed diff carrying changes outside the globs above is not your concern.
Resolve the audited root first. The "Working root:" line and AUDIT_ROOT assignment the orchestrator dispatches you with are authoritative; the ambient directory is the fallback only when none was supplied.
AUDIT_ROOT="${AUDIT_ROOT:-$PWD}"
AUDIT_ROOT="$(cd "$AUDIT_ROOT" 2>/dev/null && pwd -P)" && [ -n "$AUDIT_ROOT" ] || exit 1
printf '%s\n' "$AUDIT_ROOT"
Run it once, as its own Bash call, with the dispatched AUDIT_ROOT= assignment ahead of it when the orchestrator supplied one. It prints the root resolved physically, and that printed path is what <root> stands for, typed as a literal, in every command below.
Before the scope resolver, Read <root>/.claude/hooks/lib/audit-member-protocol.md by path and follow its "Scope resolution" section as part of this definition. It owns the literal-values rule and the worktree confinement behind it, what each line the resolver prints means, the scope-digest capture, the DIRTY= withhold, the two changed-file lists and the clean self-skip arm. Then resolve your review scope with one command:
<root>/.gaia/scripts/audit-resolve-scope.sh --member code-audit-github-workflows --root <root>
Read your own definition again only when the resolver prints DEFINITION=reread <path>; on DEFINITION=unchanged the copy you were dispatched with is current. Apply the protocol's "Scope resolution" section to everything else it prints, filtering both changed-file lists against the remit globs above.
A narrower CHANGED shifts one risk onto you: it can begin after a commit this PR already cleared (or, on a member-refusal base, refused), so a caller your delta breaks may be absent from the delta. A composite action under .github/actions/ and a job's outputs: block are both published interfaces whose callers live in other files: when either changes, git grep the action's path for uses: references and the output's name for needs.<job>.outputs.<name> reads, then check every caller against the new interface whether or not it changed. Neither break is loud. A uses: passing a with: key the action no longer declares is only rejected when that workflow next runs, and a read of a deleted output expands to the empty string rather than failing, so the first symptom is a downstream if: silently taking the wrong branch.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago Changed · -1 lines 6ec09c259e5e
- 8d ago Changed · -11 lines a84c90286512
- 10d ago Changed 7c36cfb49d71
- 11d ago Changed · +1 lines · -12 tokens per session 8969b1094c18
- 14d ago Changed · -21 lines 72f09d694d28
- 15d ago Changed e52cd88950e1
- 16d ago Changed a08fe8752b3a
- 20d ago Changed · -214 lines 57ba970b7ba7
- 21d ago Changed · +7 tokens per session 23c4bb03ffc7
- 23d ago First seen · 376 lines · 50 tokens per session scan A 1be1955b7756
code-audit-github-workflows is an agent published in the GitHub repository gaia-react/gaia (26 stars, last pushed 4d ago), licensed MIT. It adds 45 tokens to every session and 4,192 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
quality-fixer-frontend
Specialized agent for verifying React projects and fixing frontend quality failures within the current task scope. Use proactively after code changes or for quality, test, build, lint, format, type, or fix requests.
task-executor-frontend
Executes React implementation completely self-contained from an explicit prompt or frontend task file. Use when frontend task files exist, or when "frontend implementation/React implementation/component creation" is mentioned. Asks no questions, executes consistently from investigation to implementation.
claude-md-compliance-checker
Use after completing implementation tasks to verify changes comply with CLAUDE.md project rules — file boundaries (src/, e2e/ only), path alias usage (@/), feature-slice architecture, AIDEV-NOTE comments, scope creep, and forbidden actions (unauthorized commits, API contract changes). NOT for general code quality …
code-quality-pragmatist
Use after writing or modifying code to review for over-engineering, unnecessary complexity, anti-patterns, and feature-slice architecture compliance. Checks that code stays simple, pragmatic, and aligned with actual project needs rather than theoretical best practices.
ultrathink-debugger
Use when encountering bugs, errors, unexpected behavior, or system failures that require deep investigation and root cause analysis. Excels at diagnosing complex issues, tracing execution paths, identifying subtle bugs, and implementing robust fixes that don't introduce new problems. Perfect for production issues…
scraping-applier-expert
Primary reviewer for job scraping, browser automation, selector resilience, registry management, and workflow reliability. Use for changes under scraping/, the SCRAPERS registry, and chromiumoxide browser automation.