Borrowing it
Nothing to install: this file belongs to IgorGanapolsky/ThumbGate. 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/IgorGanapolsky/ThumbGate/main/.claude/skills/ci-failure-triage/SKILL.mdgit clone --depth 1 https://github.com/IgorGanapolsky/ThumbGateWrote 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/igorganapolsky/thumbgate/ci-failure-triage)<a href="https://agentmods.dev/skills/igorganapolsky/thumbgate/ci-failure-triage"><img src="https://agentmods.dev/badge/skills/igorganapolsky/thumbgate/ci-failure-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/skills/igorganapolsky/thumbgate/ci-failure-triage"><img src="https://agentmods.dev/badge/skills/igorganapolsky/thumbgate/ci-failure-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 64 Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.Fix: Set explicit rate limits, timeouts, and resource quotas for API calls, file operations, and compute. Implement circuit breakers for runaway loops.
- medium Excessive Agency · line 80 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00091 | $0.01104 |
| Opus 5 | $0.00046 | $0.00552 |
| Sonnet 5 | $0.00018 | $0.00221 |
| Haiku 4.5 | $0.00009 | $0.00110 |
Grade A, and why
ci-failure-triage scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CI Failure Triage — Read Before You Conclude
The failure this prevents
Calling a red check "transient / flaky / orphaned / stale" WITHOUT reading its body. This session: a CodeQL check failed; it was dismissed as a "transient 4s orphaned check-run" — twice — when it was reporting 3 real security vulnerabilities (2 critical command-injection + 1 high XSS). The conclusion came before the evidence. (2026 failure-triage practice = taxonomy → read → cluster → gate, a repeatable detection system, not vibes: https://latitude.so/blog/ai-agent-failure-modes-detection-playbook)
Hard rule
You may not use the words "transient", "flaky", "stale", "orphaned", or "unrelated" about a check until you have read its failure body and quoted the actual error. A duration (e.g. "4s") is a hint, never proof.
Protocol (in order — do not skip)
-
Identify the exact failing check + its commit.
head=$(gh pr view <N> --json headRefOid -q .headRefOid) gh pr checks <N> | grep -viP "\t(pass|skipping)\t" -
Read the failure body. This is the step that gets skipped.
- GitHub Actions job:
gh run view --job <id> --log-failed | tail -40 - CodeQL / code-scanning: read the ALERTS, not just the check:
gh api "repos/<owner>/<repo>/code-scanning/alerts?state=open&per_page=100" \ --jq '.[] | "\(.rule.id) | \(.rule.security_severity_level) | \(.most_recent_instance.location.path):\(.most_recent_instance.location.start_line) | ref=\(.most_recent_instance.ref)"' - Also fetch the check-run's
output.title/output.summary— it usually states exactly what failed ("2 new alerts including 2 high severity…").
- GitHub Actions job:
-
Classify against branch protection. Map each REQUIRED context to its real state on the head commit, so you know what actually blocks:
gh api repos/<owner>/<repo>/branches/main/protection/required_status_checks -q '.contexts[]' gh api "repos/<owner>/<repo>/commits/$head/check-runs" --paginate \ -q '.check_runs[] | "\(.name)=\(.conclusion)"'
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.
- 11d ago First seen · 87 lines · 91 tokens per session scan A 275f0b5e1365
ci-failure-triage is a skill published in the GitHub repository IgorGanapolsky/ThumbGate (26 stars, last pushed today), licensed MIT. It adds 91 tokens to every session and 1,104 once invoked, about $0.0005 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
learning-from-experience
Turns incidents, near misses, bad handoffs, review surprises, escaped bugs, and signals from real use into lasting fixes to your safeguards. Use after something went wrong or nearly did and a future safeguard should change. Do not use during a live incident, which comes first, or to blame someone.
reporting-shared-defects
Routes a defect found in a shared or supplied artifact (a shared prompt, skill, dependency, model, eval, or template) to the downstream teams, agents, and releases that depend on it, not just a local fix. Use when a discovered defect affects others who consume the same artifact. Do not use for a defect local to your…
responding-to-incidents
Runs a live incident the stabilize-first way — name a commander, separate facts from hypotheses, prefer reversible actions, communicate on a cadence, and drive corrective actions to closure. Use when production is broken, data is at risk, or an agent action caused harm. Do not use for routine non-incident work, or as…
actions-debugging
Use when a GitHub Actions workflow fails — diagnose the run log, identify the root cause, and apply a targeted fix.
gh-fix-ci
Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use gh to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers (for example Buildkite) as out of scope and report only the details URL.
diagnose-ci-failures
Diagnose failing CI, lint, typecheck, build, or test logs and propose or implement the smallest verified fix.