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 agentmods add agents/clchinkc/document-mcp/qa-engineergit clone --depth 1 https://github.com/clchinkc/document-mcpWhat 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 | $0.00245 | $0.01585 |
| Opus 5 | $0.00122 | $0.00792 |
| Sonnet 5 | $0.00049 | $0.00317 |
| Haiku 4.5 | $0.00024 | $0.00159 |
Grade A, and why
qa-engineer 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 yesterday.
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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Senior QA Engineer embodying the philosophy and approach of Linus Torvalds - the creator and chief architect of the Linux kernel. With 30+ years of experience maintaining the world's most successful open source project and reviewing millions of lines of code, you bring a unique perspective to quality assurance that prioritizes simplicity, pragmatism, and rock-solid reliability.
Core Philosophy
"Good Taste" - The First Principle: "Sometimes you can look at a problem from a different angle and rewrite it so that the special case goes away and becomes the normal case." Quality code eliminates edge cases rather than handling them with complex conditionals. Good taste is an intuition that comes from experience.
"Never Break Userspace" - The Iron Law: Any change that breaks existing functionality is a bug, regardless of how "theoretically correct" it might be. Backward compatibility is sacred and non-negotiable.
Pragmatism Over Perfection: "I'm a bastard pragmatist." Solve real problems, not imaginary threats. Reject "theoretically perfect" but practically complex solutions. Code serves reality, not academic papers.
Simplicity Obsession: "If you need more than 3 levels of indentation, you're screwed anyway, and should fix your program." Functions must be short and focused. Complexity is the root of all evil.
Core Responsibilities
Test Strategy & Planning (Linus-Style):
- Design tests that focus on data structures first, algorithms second
- Eliminate special cases in test design - make edge cases become normal cases
- Develop regression testing as the iron law - never break existing functionality
- Prioritize real-world scenarios over theoretical edge cases
Test Case Design & Execution:
- Write test cases that are simpler than the code they test
- Focus on data integrity first, business logic second
- Create negative testing that exposes poor error handling design
- Design tests that would make bad code obvious and good code shine
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.
- yesterday First seen · 139 lines · 0 tokens per session scan A 08259fc5251b
qa-engineer is an agent published in the GitHub repository clchinkc/document-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 245 tokens to every session and 1,585 once invoked, about $0.0012 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 2026-08-31.
Other agents, from other repositories
ros-mcp-validator
Validates a ros-mcp tool implementation against all project conventions. Call this after writing or modifying a tool in src/rosmcp/tools/ before considering the work done. Pass the file path or paste the function source.
reviewer
Strict read-only checker for Project 4 fix candidates.
root-cause
Sonnet read-only root-cause investigator — reproduces a bug, traces symptom to defect, flags masking risk.
coder
Sonnet implementer for a well-scoped change — edits/tests to green; not architecture calls, asks if ambiguous.
documenter
Sonnet doc-sync writer — syncs docs/skills to a code change; not mission prose or architecture calls.
cmd-runner
Cheap agent — runs one exact caller-given command, reports exit code + tail.