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 vasilyu1983/AI-Agents-public --skill qa-debugginggit clone --depth 1 https://github.com/vasilyu1983/AI-Agents-publicWrote 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/vasilyu1983/ai-agents-public/qa-debugging)<a href="https://agentmods.dev/skills/vasilyu1983/ai-agents-public/qa-debugging"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/qa-debugging/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/vasilyu1983/ai-agents-public/qa-debugging"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/qa-debugging.svg" alt="Reviewed on agentmods" width="80" 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 | $0.04855 |
| Opus 5 | $0.00016 | $0.02427 |
| Sonnet 5 | $0.00007 | $0.00971 |
| Haiku 4.5 | $0.00003 | $0.00485 |
Grade A, and why
qa-debugging 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 9d 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 — 391 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Debugging
Use systematic debugging to turn symptoms into evidence, then into a verified fix with a regression test and prevention plan.
Default stance:
- Keep debugging evidence-first: reproduce, isolate, measure, then change one variable at a time.
- Treat logs, metrics, traces, and profiles as the default production debugging substrate.
- When telemetry implementation is missing or broken, hand off setup work to
../qa-observability/SKILL.md. - For agentic systems, debug the full chain: user input, prompt/version, retrieval context, tool calls, model output, and guardrails.
Quick Reference
| Need | Go to |
|---|---|
| Run the debugging sequence | ## Default Workflow (Reproduce -> Isolate -> Instrument -> Fix -> Verify -> Prevent) |
| Pick the right triage branch | ## Triage Tracks (Pick The First Branch That Fits) |
| Search known errors before debugging from scratch | ## Search The Validated Corpus First (Recognizable Failures) |
| Apply production-safe debugging | ## Production & Incident Safety |
| Decide when to stop guessing, escalate to design fix, or catch a cognitive trap | ## Expert Judgment (What a Checklist Misses) |
| Load references and templates | ## Navigation |
Quick Start
Intake (Ask First)
- Capture the failure signature: error message, stack trace, request ID/trace ID, timestamp, build SHA, environment, affected user/tenant.
- For browser/E2E issues, capture the exact repro command plus trace/error-context artifact path before changing anything.
- Confirm expected vs actual behavior, plus the smallest reliable reproduction steps (or “cannot reproduce” explicitly).
- Ask “when did this start?” and “what changed?” (deploy, flag, config, data, dependency, infra).
- Identify blast radius and urgency: who/what is impacted, and whether this is an incident.
Output Shape (Default)
- Summary of symptoms + confirmed facts
- Top hypotheses (ranked) with evidence and disconfirming tests
- Next experiments (smallest, fastest, safest) with expected outcomes
- Fix options (root-cause) + verification plan + regression test target
- If production-impacting: mitigation/rollback plan + rollout + prevention
What ships with it
22 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.
- agents/openai.yaml 325 B
- assets/debugging/template-debugging-checklist.md 8.7 KB
- assets/debugging/template-debugging-worksheet.md 2.2 KB
- assets/debugging/template-root-cause-to-guardrail.md 1.1 KB
- assets/incidents/template-incident-response.md 14 KB
- assets/observability/template-logging-setup.md 15 KB
- data/sources.json 11 KB
- learnings.consolidated.md 588 B
- learnings.md 592 B
- references/causal-inference-applied.md 41 KB
- references/debugging-methodologies.md 17 KB
- references/distributed-debugging.md 21 KB
- references/external-input-normalization-boundary.md 1.2 KB
- references/logging-best-practices.md 13 KB
- references/memory-leak-detection.md 17 KB
- references/operational-patterns.md 24 KB
- references/production-debugging-patterns.md 14 KB
- references/race-condition-diagnosis.md 20 KB
- references/stackoverflow-for-agents.md 7.2 KB
- references/systems-debugging-tools.md 12 KB
- scripts/config_diff.py 7.5 KB runs code
- scripts/log_error_summary.py 5.1 KB runs code
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.
- 9d ago First seen · 391 lines · 33 tokens per session scan A 7b50d536a2b3
qa-debugging is a skill published in the GitHub repository vasilyu1983/AI-Agents-public (87 stars, last pushed 10d ago), licensed MIT. It adds 33 tokens to every session and 4,855 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 2026-09-03.
Other skills, from other repositories
debugging-strategies
Master systematic debugging techniques, profiling tools, and root cause analysis to efficiently track down bugs across any codebase or technology stack. Use when investigating bugs, performance issues, or unexpected behavior.
git-advanced-workflows
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
sql-optimization-patterns
Master SQL query optimization, indexing strategies, and EXPLAIN analysis to dramatically improve database performance and eliminate slow queries. Use when debugging slow queries, designing database schemas, or optimizing application performance.
parallel-debugging
Debug complex issues using competing hypotheses with parallel investigation, evidence collection, and root cause arbitration. Use this skill when debugging bugs with multiple potential causes, performing root cause analysis, or organizing parallel investigation workflows.
error-handling-patterns
Master error handling patterns across languages including exceptions, Result types, error propagation, and graceful degradation to build resilient applications. Use when implementing error handling, designing APIs, or improving application reliability.
spark-optimization
Optimize Apache Spark jobs with partitioning, caching, shuffle optimization, and memory tuning. Use when improving Spark performance, debugging slow jobs, or scaling data processing pipelines.