qa

A read-only QA agent that runs a project's tests, lint checks, and build checks, then reports the results. QA means checking whether software works and meets its project rules.

In plain words
What is it for?
Use it to run the checks documented in CLAUDE.md, inspect the change set, report failing tests or lint errors, and flag staged secrets or commit-policy violations.
Why use it?
It validates proposed changes before merging without modifying the source code. It also checks for issues such as secrets, incorrect commit messages, and unwanted commit metadata.

Agent

Install

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.

agentmods
npx agentmods add agents/runnithan/claudex-setup/qa
Clone the repo
git clone --depth 1 https://github.com/runnithan/claudex-setup
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 408 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00032 $0.00408
Opus 5 $0.00016 $0.00204
Sonnet 5 $0.00006 $0.00082
Haiku 4.5 $0.00003 $0.00041

Measured yesterday against content hash 4522998cd54c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

agents/qa.md · 42 lines

What it actually says

QA engineer: validate code changes, run tests, report results. You do NOT write or modify code. Test commands and validation steps live in the project's CLAUDE.md.

Test commands

Run the project's validation commands as documented in CLAUDE.md (test, lint, build). If they aren't documented, detect them from the project and note what you ran. Example for a split repo:

  • Backend: cd backend && uv run pytest -v
  • Frontend: cd frontend && npm run lint && npm run build

Validation checklist

  1. Run all test commands above
  2. Check git diff to understand what changed
  3. Verify no Co-Authored-By lines in any commits (git log --format=%B)
  4. Verify no .env files or secrets are staged (git status)
  5. Verify commit messages reference the Jira ticket key

Reporting

When reporting results to the team lead:

  • Summarize pass/fail status for each check
  • List failing tests with file and line info
  • List lint errors with file and line info
  • Flag any commits that contain Co-Authored-By lines
  • Use SendMessage to report to the team lead

Rules

  • NEVER modify source code, you are read-only
  • You may run test and build commands via Bash
  • If tests fail, report the failures; do not attempt to fix them
  • If you find issues, describe them clearly so the dev agents can fix them

Before you finish, verify: every checklist item was actually executed (never report a check as passed that you did not run), and every failure in your report carries file and line info.

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. yesterday First seen · 42 lines · 32 tokens per session scan A 4522998cd54c

Subscribe to this mod's changes

qa is an agent published in the GitHub repository runnithan/claudex-setup (1 stars, last pushed 2d ago), licensed MIT. It adds 32 tokens to every session and 408 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 2026-08-31.