Borrowing it
Nothing to install: this file belongs to Terry-Mao/AICodingFlow. 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/Terry-Mao/AICodingFlow/main/.agents/skills/diagnose-ci-failures/SKILL.mdgit clone --depth 1 https://github.com/Terry-Mao/AICodingFlowWrote 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/skills/terry-mao/aicodingflow/diagnose-ci-failures)<a href="https://agentmods.dev/skills/terry-mao/aicodingflow/diagnose-ci-failures"><img src="https://agentmods.dev/badge/skills/terry-mao/aicodingflow/diagnose-ci-failures.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00033 | $0.00389 |
| Opus 5 | $0.00016 | $0.00195 |
| Sonnet 5 | $0.00007 | $0.00078 |
| Haiku 4.5 | $0.00003 | $0.00039 |
Grade A, and why
diagnose-ci-failures 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 8d 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.
What it actually says
diagnose-ci-failures
Use this when the user asks to inspect failing CI. This skill is diagnosis-only: it produces a reviewable plan and does not edit, commit, push, or create PRs.
Find and inspect the target
Use the user's run URL, run ID, or branch when provided. Otherwise inspect the current branch's PR and failed checks, then fall back to recent failed runs for that branch. If no failing target exists, report that and stop.
gh run view <run-id> --verbose
gh run list --branch <branch> --status failure --limit 5
gh pr view --json number,title,url,state,statusCheckRollup
For the selected PR/run, identify completed, pending, passed, and failed checks. If checks are still running, report the partial state instead of guessing. Pull failed-step logs first:
gh run view <run-id> --log-failed
Inspect a specific job or download artifacts only when the failed-step output is insufficient. Extract observed paths, line numbers, error messages, failing tests, stack traces, and environment/permission failures.
Produce the plan
Group evidence into build/compile, test, lint/format, and environment/setup failures. Do not assume a language, tool, or root cause before repository files or logs establish it. Write a plan containing:
- problem statement and affected checks;
- current evidence and locations;
- likely root cause grounded in the logs;
- specific proposed changes;
- validation steps for the follow-up implementation.
Prefer CI evidence over local guesses. Treat multiple unrelated failures as separate categories and recommend resolving them one category at a time.
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.
- 8d ago First seen · 49 lines · 33 tokens per session scan A 00597e10e7af
diagnose-ci-failures is a skill published in the GitHub repository Terry-Mao/AICodingFlow (165 stars, last pushed 10d ago), licensed MIT. It adds 33 tokens to every session and 389 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
smoke-test
Health smoke tests + auto-fix for gbrain installs (and OpenClaw services when present). Run after machine/container restarts or whenever something seems broken. Tests critical services, auto-fixes bounded local issues, and reports worker topology without starting daemons. Extensible via user-defined test scripts in…
mcore-create-issue
Investigate a failing GitHub Actions run or job and create a GitHub issue for the failure.
debug-task
Diagnose and fix moon tasks that are broken, misconfigured, or behaving unexpectedly. Use this skill when a moon task is failing, not running, skipped, hanging, producing stale or wrong output, cached when it shouldn't be, re-running every time when it should be cached, or when outputs are empty or missing after a…
github-ci-fix
Fix failing GitHub CI / Actions checks via fixgithubprci and push to the existing PR head, or fix a branch's failing CI via a linked repair worktree.
github-ci-fix
Use when the user asks OpenSRE to fix failing GitHub CI, GitHub Actions checks, failing pull request checks, a broken PR branch, or CI on a named branch such as main.
ci-triage
Classify CI failures — distinguish clear regressions from infra flakes and security-test failures. Produces structured failure reports.