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 skills/suyoumo/clawprobench/qa-reviewnpx skills add suyoumo/ClawProBench --skill qa-reviewgit clone --depth 1 https://github.com/suyoumo/ClawProBenchWrote 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/skills/suyoumo/clawprobench/qa-review)<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>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 | $0.00030 | $0.00993 |
| Opus 5 | $0.00015 | $0.00496 |
| Sonnet 5 | $0.00006 | $0.00199 |
| Haiku 4.5 | $0.00003 | $0.00099 |
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.
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
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.
- 6d ago First seen · 130 lines · 30 tokens per session scan A 4b7a9aaedcd2
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.
Other skills, from other repositories
Evaluation
Frames model, prompt, and system evaluation as a reproducible experiment with baselines, datasets, and explicit metrics.
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…
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…
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.
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…
benchmark-design
Design and calibrate a multi-Case capability Benchmark and establish a traceable Formal Baseline.