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.
npx skills add petrkindlmann/qa-skills --skill ai-bug-triagegit clone --depth 1 https://github.com/petrkindlmann/qa-skillsWrote 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/petrkindlmann/qa-skills/ai-bug-triage)<a href="https://agentmods.dev/skills/petrkindlmann/qa-skills/ai-bug-triage"><img src="https://agentmods.dev/badge/skills/petrkindlmann/qa-skills/ai-bug-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/petrkindlmann/qa-skills/ai-bug-triage"><img src="https://agentmods.dev/badge/skills/petrkindlmann/qa-skills/ai-bug-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- 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 | $0.00148 | $0.04960 |
| Opus 5.5 | $0.00059 | $0.01984 |
| Sonnet 5.5 | $0.00030 | $0.00992 |
| Haiku 4.5 | $0.00015 | $0.00496 |
Grade A, and why
ai-bug-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 1mo 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 — 418 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Key reframe: The LLM is best at explaining and routing, not deduplication. Teach agents to DESIGN the pipeline, not BE the pipeline.
Discovery Questions
Check .agents/qa-project-context.md first — it carries tech stack, component mapping, and known flaky areas that improve classification accuracy. Use it and skip anything already answered there. Then clarify:
-
What is the failure source?
- CI pipeline logs (GitHub Actions, GitLab CI, Jenkins, CircleCI)
- Test framework output (Playwright, Jest, pytest, Vitest)
- Production error monitoring (Sentry, Datadog, Bugsnag)
- Manual bug reports from QA or users
-
What is the ticket destination?
- Jira, Linear, GitHub Issues, Azure DevOps, Shortcut
- What fields are required? (component, severity, priority, labels)
- What workflows exist? (triage board, auto-assignment rules)
-
What is the deduplication scope?
- Same test run? Same sprint? Same release? All time?
- Do you already have fingerprinting? What is the current duplicate rate?
-
What approval workflow is needed?
- Auto-create tickets with human review?
- Suggest tickets for human approval before creation?
- Auto-close duplicates? (dangerous -- require approval)
-
What historical data exists?
- Past bug reports with resolution data?
- Flaky test history? Known environment issues?
- Component ownership mapping?
Core Principles
-
Deterministic first, LLM second. Use stable, reproducible fingerprinting for deduplication and clustering. Use LLM only for tasks requiring understanding: severity classification, root cause hypothesis, and human-readable ticket writing.
-
Normalize before comparing. Raw CI logs are full of timestamps, port numbers, process IDs, and random suffixes that make identical failures look different. Strip all noise before fingerprinting.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 418 lines · 148 tokens per session scan A 17b7e094eb8f
ai-bug-triage is a skill published in the GitHub repository petrkindlmann/qa-skills (214 stars, last pushed 5d ago), licensed MIT. It adds 148 tokens to every session and 4,960 once invoked, about $0.0006 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 skills, from other repositories
GitHub CI Fix Debugging
Debug and fix failing GitHub PR checks by inspecting GitHub Actions logs, summarizing failure context, drafting fix plans, and implementing fixes after approval.
afrexai-performance-engineering
Complete performance engineering system — profiling, optimization, load testing, capacity planning, and performance culture. Use when diagnosing slow applications, optimizing code/queries/infrastructure, load testing before launch, planning capacity, or building performance into CI/CD. Covers Node.js, Python, Go…
operating-github-ci-fixer
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.
reproduce-and-fix-issues
Reproduce triaged Slack bugs through a configured app-control adapter, verify existing fixes, and open a bounded draft pull request only after before-and-after proof. Use only from the configured Benny repro automation.
meta-long-running-build-watchdog
Watches a long-running command via tmux, lets sub-agent diagnose failures and propose a fix, and records the diagnosis to memory. Designed for overnight model fine-tunes, CI image builds, or repeated regression suites that may fail intermittently.
analyze-ci
Analyze failed GitHub Action jobs for a pull request.