Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/sigistry/marketplaceWrote 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/commands/sigistry/marketplace/gha-triage)<a href="https://agentmods.dev/commands/sigistry/marketplace/gha-triage"><img src="https://agentmods.dev/badge/commands/sigistry/marketplace/gha-triage/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/commands/sigistry/marketplace/gha-triage"><img src="https://agentmods.dev/badge/commands/sigistry/marketplace/gha-triage.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 | $0.00014 | $0.00801 |
| Opus 5 | $0.00007 | $0.00400 |
| Sonnet 5 | $0.00003 | $0.00160 |
| Haiku 4.5 | $0.00001 | $0.00080 |
Grade A, and why
gha-triage 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 12d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Triage a failing GitHub Actions run and return the root cause with an exact YAML fix. Use this the moment a workflow goes red and you want to stop guessing. $ARGUMENTS may be a path to a workflow file (e.g. .github/workflows/ci.yml), a job/step name, or a block of pasted failure logs, often both.
Process
Step 1: Gather the evidence
- If
$ARGUMENTSnames a workflow file, read it. Otherwise glob.github/workflows/*.ymland.github/workflows/*.yamland read every workflow. - Capture any pasted log excerpt from
$ARGUMENTS. Note the exact error line, the failing job name, the stepname/uses/run, and the runner label (runs-on). - Look for the annotation GitHub prints:
Error: Process completed with exit code N,Resource not accessible by integration,The secret ... was not found,no matching workflow run, etc. These strings are the fastest classifiers.
Step 2: Classify the failure
Apply the gha-failure-taxonomy skill. Map the symptom to exactly one primary class:
| Class | Tell-tale signal in logs |
|---|---|
Permissions / GITHUB_TOKEN scope |
Resource not accessible by integration, 403 on push/PR/packages |
| Missing / misnamed secret | secret ... not found, empty env var, auth failure with no token |
| Matrix expansion | job runs 0 times, matrix key typo, fail-fast cancels siblings |
| Cache miss | Cache not found for input keys, cold installs every run |
| Trigger mismatch | workflow "didn't run", on: paths/branches filter excludes the ref |
| Checkout depth | fatal: ... shallow, missing tags, git describe fails |
| Concurrency cancellation | Canceling since a higher priority ... exists |
| Runner / tool drift | command not found, version mismatch, latest runner image change |
| OIDC / cloud auth | Not authorized to perform sts:AssumeRoleWithWebIdentity, missing id-token: write |
| Flaky / network | timeouts, ECONNRESET, passes on re-run |
Step 3: Pinpoint and confirm
- Cite the offending step by
file:line. Quote the exact log line that proves it. - For multi-workflow repos, or when the failing step spans reusable/called workflows, launch the ci-failure-triager agent to correlate across files and, where safe, reproduce the failing lint/test/build command locally.
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.
- 12d ago First seen · 49 lines · 14 tokens per session scan A 2ac1dc49d713
gha-triage is a command published in the GitHub repository sigistry/marketplace (3 stars, last pushed yesterday), licensed MIT. It adds 14 tokens to every session and 801 once invoked, about $0.0001 per session on Opus 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 2026-08-31.
Other commands, from other repositories
pipeline
Add and validate CI/CD workflows one bundle at a time.
typescript-dev
Start TypeScript development workflow with architecture, implementation, review, and testing phases.
audit-security
Check baseline CI security hygiene against the Starter Series bar — gitleaks, CodeQL, dep audit, license check, --ignore-scripts, Dependabot grouped, secret-scanning, claude-code-security-review, claude-security-guidance. Read-only, complementary to Anthropic's in-session security guidance plugin.
compliance-fix
Show Qualimetry review findings for a file and apply the standards-compliant fix.
f5-checkpoint
This command has been consolidated into /f5-ctx.
f5-codebase
This command has been consolidated into /f5-memory codebase.