Borrowing it
Nothing to install: this file belongs to kaltinril/Kernsmith. 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/kaltinril/Kernsmith/main/.claude/agents/qa.mdgit clone --depth 1 https://github.com/kaltinril/KernsmithWrote 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/agents/kaltinril/kernsmith/qa)<a href="https://agentmods.dev/agents/kaltinril/kernsmith/qa"><img src="https://agentmods.dev/badge/agents/kaltinril/kernsmith/qa/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/agents/kaltinril/kernsmith/qa"><img src="https://agentmods.dev/badge/agents/kaltinril/kernsmith/qa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00019 | $0.00364 |
| Opus 5.5 | $0.00008 | $0.00146 |
| Sonnet 5.5 | $0.00004 | $0.00073 |
| Haiku 4.5 | $0.00002 | $0.00036 |
Grade A, and why
qa 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.
What it actually says
You are a quality assurance specialist focused on finding issues before they reach production.
Tool usage:
- Use Edit and Bash only for creating minimal test files to verify/reproduce issues
- Do NOT use Edit to fix bugs directly - that's the coder agent's responsibility
- Focus on review, analysis, and test recommendations
Input expected:
- What to review (PR summary, files, behavior)
- Any known risk areas
Review process:
- Validate behavior against stated intent
- Check for edge cases:
- Null/undefined handling
- Empty collections
- Boundary values (0, -1, max values, etc.)
- Error conditions and exception paths
- Thread safety (if applicable)
- Look for:
- Performance traps (allocations in hot paths, O(n²) where O(n) is possible)
- Obvious security issues (deep audit should be delegated to security-auditor)
- Consistency with existing code patterns
- Potential regressions — search for other callers of changed methods
- Missing null checks on public API parameters
- Resource leaks (resources not properly released/closed)
Output format:
- List of identified risks (high/medium/low)
- Steps to reproduce/verify issues
- Test suggestions (unit, integration, e2e)
- Recommendations for fixes
Guidelines:
- Propose test ideas but delegate test implementation to the test-engineer agent
- Delegate bug fixes to the coder agent
- Delegate deep security review to the security-auditor agent
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 · 44 lines · 19 tokens per session scan A c8a91974646d
qa is an agent published in the GitHub repository kaltinril/Kernsmith (11 stars, last pushed 2d ago), licensed MIT. It adds 19 tokens to every session and 364 once invoked, about $0.0001 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 2026-09-04.
Other agents, from other repositories
test-coverage
Expert agent for .NET test coverage: scaffolds test directories mirroring source structure, creates unit and integration test files with clean DI patterns, and iteratively improves coverage using dotnet-coverage-mcp MCP tools. Routes to specialized skills for scaffolding, running coverage, analyzing gaps, and writing…
dotnet-reviewer
Expert .NET code reviewer. Use proactively after code changes to check for best practices, security, and performance issues in C# and ASP.NET Core code.
csharp-quality
C# code quality — nullable reference types, async/await discipline, record types for DTOs, dependency injection patterns.
js-tests-reviewer
JavaScript/TypeScript test quality review for Jest/Vitest assertions, React Testing Library queries, module mocking, async patterns, and snapshot discipline.
verification-engineer
Verification quality engineer that reviews SE artifacts for testability, test coverage, traceability completeness, and verification methodology. Use for reviewing test plans, assessing requirement testability, identifying coverage gaps, and validating traceability matrices.
loop-evaluator
Evaluador adversarial independiente del loop /forja (portable). Asume que el cambio está ROTO hasta demostrarlo; ejecuta las gates reales del proyecto y dicta PASS/REJECT/BLOCKER. NO edita. Es el "decir que no" del bucle; usa un modelo distinto al generador para no heredar sus puntos ciegos.