ThumbGate: Skill for Claude Code

.claude/skills/ci-failure-triage/SKILL.md

ci-failure-triage is a skill for Claude Code from IgorGanapolsky/ThumbGate. It costs 91 tokens per session (1,104 once invoked), scanned A, original, MIT.

A procedure for investigating failed continuous-integration checks, the automated tests and checks that run on a code change, by reading the reported error first.

In plain words
What is it for?
Use it when a pull request is blocked, a required check fails, or you need to determine whether a failure is real, repeated, outdated, or unrelated.
Why use it?
It prevents dismissing a failed check as temporary or irrelevant without checking what actually went wrong.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is IgorGanapolsky/ThumbGate's own configuration. It tells Claude Code how to work on ThumbGate itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ThumbGate configures →

Part of the thumbgate plugin — 37 skills, 7 commands, 1 agent, 5 hooks, 2 MCP servers, 2 plugins shipped together

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/IgorGanapolsky/ThumbGate/main/.claude/skills/ci-failure-triage/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/IgorGanapolsky/ThumbGate

Made for: Claude Code.

Or install thumbgate, the plugin that ships this one along with the rest of its 37 skills, 7 commands, 1 agent, 5 hooks, 2 MCP servers, 2 plugins.

Wrote 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.

agentmods badge for ci-failure-triage

README.md
[![agentmods](https://agentmods.dev/badge/skills/igorganapolsky/thumbgate/ci-failure-triage/github.svg)](https://agentmods.dev/skills/igorganapolsky/thumbgate/ci-failure-triage)
Your own site
<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.

agentmods 80×15 button for ci-failure-triage

Your own site · 80×15
<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>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,104 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
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.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 11d ago against content hash 275f0b5e1365, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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.

.claude/skills/ci-failure-triage/SKILL.md · 87 lines

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)

  1. 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"
    
  2. 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…").
  3. 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)"'
    

Read the full file on GitHub · 87 lines

Changes

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.

  1. 11d ago First seen · 87 lines · 91 tokens per session scan A 275f0b5e1365

Subscribe to this mod's changes

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.

Related

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.

FlyFission/nuclear-grade-context-engineering · 65 tokens

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…

FlyFission/nuclear-grade-context-engineering · 93 tokens

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…

FlyFission/nuclear-grade-context-engineering · 80 tokens

actions-debugging

Use when a GitHub Actions workflow fails — diagnose the run log, identify the root cause, and apply a targeted fix.

drvoss/everything-copilot-cli · 28 tokens

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.

rojim666/SztuCode · 72 tokens

diagnose-ci-failures

Diagnose failing CI, lint, typecheck, build, or test logs and propose or implement the smallest verified fix.

PyModel/pythinker-cli · 31 tokens