qa-review

qa-review is a skill for Claude Code, Codex from suyoumo/ClawProBench. It costs 30 tokens per session (993 once invoked), scanned A, original, Apache-2.0.

A quality-assurance review skill for code changes. QA, or quality assurance, checks whether software behaves correctly, including error cases, unusual inputs, and possible regressions.

In plain words
What is it for?
Use it to review test coverage, identify edge cases such as empty or invalid input, create a test plan, and assess regression risk.
Why use it?
It finds missing tests and failure scenarios before changes are merged. It checks whether existing tests actually verify behavior instead of merely existing.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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 skills/suyoumo/clawprobench/qa-review
Any agent
npx skills add suyoumo/ClawProBench --skill qa-review
Clone the repo
git clone --depth 1 https://github.com/suyoumo/ClawProBench

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for qa-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/suyoumo/clawprobench/qa-review.svg)](https://agentmods.dev/skills/suyoumo/clawprobench/qa-review)
Your own site
<a href="https://agentmods.dev/skills/suyoumo/clawprobench/qa-review"><img src="https://agentmods.dev/badge/skills/suyoumo/clawprobench/qa-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 993 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 5.1 $0.00030 $0.00993
Opus 5 $0.00015 $0.00496
Sonnet 5 $0.00006 $0.00199
Haiku 4.5 $0.00003 $0.00099

Measured 6d ago against content hash 4b7a9aaedcd2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

qa-review 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 6d 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.

ironclaw/skills/qa-review/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QA Review

You are a QA engineer reviewing code for test coverage, edge cases, and regression risks. Focus on what breaks in production, not theoretical completeness.

When to run

  • Before merging PRs with logic changes
  • When user asks about test coverage or edge cases
  • As part of the review readiness pipeline (/review-readiness)
  • When the weekly retro shows declining test health

Review methodology

1. Coverage analysis

  • Identify changed functions/modules and check for corresponding tests
  • Flag untested code paths: error handlers, edge cases, boundary conditions
  • Check test quality, not just existence — a test that never asserts is worse than no test

2. Edge case identification

For each changed function, consider:

  • Boundary values: empty input, zero, max int, single element, exactly-at-limit
  • Type boundaries: null/None/nil, empty string vs missing, NaN, negative numbers
  • Concurrency: race conditions, concurrent access, timeout during operation
  • State transitions: invalid state transitions, repeated calls, out-of-order operations
  • External failures: network timeout, disk full, permission denied, malformed response

3. Regression risk assessment

  • What existing behavior could break from these changes?
  • Are integration tests covering the changed interaction paths?
  • Are there implicit dependencies that tests don't capture?

4. Test plan generation

When asked to generate a test plan, produce:

## Test Plan — <feature/PR>

### Unit Tests
- [ ] <test description> — covers: <what scenario>
- [ ] <test description> — covers: <edge case>

### Integration Tests
- [ ] <test description> — covers: <interaction between modules>

### Regression Tests
- [ ] <test description> — ensures: <existing behavior preserved>

### Manual Verification
- [ ] <step> — verify: <expected outcome>

5. Test health metrics

Track over time (via weekly retro integration):

  • Test-to-code ratio: lines of test per lines of production code
  • Flaky test rate: tests that pass/fail non-deterministically
  • Coverage trend: improving or declining
  • Time-to-test: how long the test suite takes

Read the full file on GitHub · 130 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. 6d ago First seen · 130 lines · 30 tokens per session scan A 4b7a9aaedcd2

Subscribe to this mod's changes

qa-review is a skill published in the GitHub repository suyoumo/ClawProBench (823 stars, last pushed 11d ago), licensed Apache-2.0. It adds 30 tokens to every session and 993 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 2026-08-30.

Related

Other skills, from other repositories

Evaluation

Frames model, prompt, and system evaluation as a reproducible experiment with baselines, datasets, and explicit metrics.

agentic-in/elephant-agent · 25 tokens

harness-creator

Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…

walkinglabs/learn-harness-engineering · 142 tokens

remote-claude-code

Run Claude Code on a remote host over SSH — a persistent expect-driven login session, headless claude -p with the stdin fix, the interactive TUI inside a remote tmux driven by send-keys/capture-pane (one keystroke at a time, capture-verified; relayed user messages go through verbatim), and multi-turn continuity via…

Prism-Shadow/penguin-harness · 107 tokens

unified-llm-api

Call model APIs through @prismshadow/agenthub — streaming text generation, image generation, speech synthesis, embeddings and the supported-model registry with one client.

Prism-Shadow/penguin-harness · 39 tokens

penguin-harness-dev

Use when developing PenguinHarness itself — changing packages/{core,server,web,cli,desktop,landing,docs,skills}, the built-in model catalog, the installers or the release workflow; writing or auditing changelog entries; writing a blog post or capturing release screenshots; deciding what to do about data already on…

Prism-Shadow/penguin-harness · 119 tokens

benchmark-design

Design and calibrate a multi-Case capability Benchmark and establish a traceable Formal Baseline.

Prism-Shadow/penguin-harness · 22 tokens