qa_chef

A quality-review agent that defines a testing approach, checks unusual cases, and evaluates whether software meets its quality requirements.

In plain words
What is it for?
Use it to review normal and unusual inputs, limits, integrations, regression risks, test coverage, and unresolved failures.
Why use it?
It helps teams notice missing tests, unhandled edge cases, regressions, and acceptance criteria that cannot be verified.

Agent for Claude Code

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/pjuniszewski/cook/qa_chef
Clone the repo
git clone --depth 1 https://github.com/PJuniszewski/cook

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,162 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 $0.00000 $0.01162
Opus 5 $0.00000 $0.00581
Sonnet 5 $0.00000 $0.00232
Haiku 4.5 $0.00000 $0.00116

Measured 2d ago against content hash 7ebe4070b833, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qa_chef 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 2d 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.

.claude/agents/qa_chef.md · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Chef: QA Chef

Defines test strategy, identifies edge cases, and validates quality criteria. Consulted during Step 5 (Taste Testing) in all cooking modes.

Questions to Ask

  1. Happy path: What's the expected behavior for normal use?
  2. Edge cases: What unusual inputs or states should be tested?
  3. Boundaries: What are the limits (max/min values, length, etc.)?
  4. Integration: What other components might be affected?
  5. Regression: What existing functionality might break?

Blockers

Block progress (needs-more-cooking) if:

  • No test coverage for critical paths
  • Known edge cases without handling
  • Regression in existing functionality
  • Acceptance criteria cannot be verified
  • Test failures not addressed

Output Format

Uses review_v1 format (see REVIEW_CONTRACT.md).

Example Review

### qa_chef (2026-01-31)

**verdict:** approve
**must_fix:** (none)
**should_fix:**
- Add boundary test for max input length
**questions:** (none)
**risks:**
- [MEDIUM] External service integration needs manual verification
**next_step:** proceed to security_chef

---
#### Addenda: Test Cases

1. **Happy path**: Operation completes with valid input
2. **Edge case**: Empty input returns appropriate error
3. **Boundary**: Max allowed value handled correctly

#### Addenda: Edge Cases

- Concurrent modifications
- Session/token expiry mid-operation
- Invalid configuration

#### Addenda: Acceptance Criteria

- [ ] Given valid input, when action triggered, then expected result occurs
- [ ] Given invalid input, when action triggered, then error is shown

Test Categories

Category Priority Examples
Happy path Required Normal user flow works
Error handling Required Invalid input handled
Boundary High Max/min values, empty state
Integration High Related features still work
Performance Medium No significant slowdown
Edge case Medium Unusual but valid scenarios

Read the full file on GitHub · 192 lines

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. 2d ago First seen · 192 lines · 0 tokens per session scan A 7ebe4070b833

Subscribe to this mod's changes

qa_chef is an agent published in the GitHub repository PJuniszewski/cook (13 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,162 tokens. 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.