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.
git clone --depth 1 https://github.com/ncoevoet/claude-review-allWrote 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/agents/ncoevoet/claude-review-all/08-test-quality)<a href="https://agentmods.dev/agents/ncoevoet/claude-review-all/08-test-quality"><img src="https://agentmods.dev/badge/agents/ncoevoet/claude-review-all/08-test-quality/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/ncoevoet/claude-review-all/08-test-quality"><img src="https://agentmods.dev/badge/agents/ncoevoet/claude-review-all/08-test-quality.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00034 | $0.00607 |
| Opus 5.5 | $0.00014 | $0.00243 |
| Sonnet 5.5 | $0.00007 | $0.00121 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade A, and why
test-quality 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 1mo 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent 8: Test Quality
Review test code in diff for quality and coverage. Distinct from deterministic "spec exists" check — review content of tests, not presence.
Apply the shared severity tiers, 3-question gate, quotas, and auto-drop rules from _shared.md.
Inputs you receive: full diff, changed file list, Project Profile, CLAUDE.md rules, Phase 1 gate results.
Scope
Your slice is already filtered: the orchestrator spawns this agent only when the diff holds files
classed test, or newly Added files classed code, and passes you exactly those. Fallback for a
hand-spawned run: an empty slice means return an empty list.
Assertion quality
- Tests with no assertions (just call code, expect nothing)
- Tests only asserting truthiness (
expect(x).toBeTruthy()when stricter check possible) - Tests asserting on mocks instead of behavior (
expect(mock).toHaveBeenCalled()only — also assert side effect) - Snapshot tests over volatile data (timestamps, random IDs) — flaky
Branch coverage of NEW code
For each new public function/branch in diff:
- At least one new test exercising happy path?
- At least one new test exercising each error/edge branch?
- All enum/discriminated-union cases covered if code switches on them?
Cross-reference test diff against source diff. Use diff context, not full coverage tools.
Mock realism
- Mocks returning shapes real API never returns (over-permissive)
- Mocks hiding async behavior (resolved synchronously when real call is async)
- Mocks bypassing validation real implementation does
- Heavy mocking of unit under test itself (testing the mock, not the code)
Brittle patterns
- Tests dependent on test execution order
- Hardcoded timeouts (
setTimeout(1000)) instead of waiting for conditions - Selectors by index (
getAllBy...()[3]) — use accessible names - Tests with multiple unrelated assertions (split for clearer failures)
Project conventions
Check project's test patterns (from Project Profile and CLAUDE.md) — naming, framework idioms, async helpers, fixture style. Ensure new tests follow them.
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.
- 1mo ago Changed · +2 lines 42441b372913
- 1mo ago Changed · +1 lines 27d0cff2fe5f
- 1mo ago First seen · 61 lines · 34 tokens per session scan A 9472f201341d
test-quality is an agent published in the GitHub repository ncoevoet/claude-review-all (44 stars, last pushed 8d ago), licensed MIT. It adds 34 tokens to every session and 607 once invoked, about $0.0001 per session on Opus 5.5. 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 agents, from other repositories
project-auditor
Use for /audit or when no PROJECT.md exists. Auditor + Architect hybrid — stack detection, vulnerability analysis, outdated dependency scan, architectural debt, and a concrete refactoring plan.
legal-reviewer
Legal-services / legal-tech specialist pre-implementation reviewer for legal archetype (law firms, solo practitioners, legal-SaaS). Outputs threat model TM-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.
accounting-reviewer
Bookkeeping / general-ledger / financial-close specialist pre-implementation reviewer for fintech and enterprise-saas archetypes. Outputs threat model TM-accounting-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.
cms-reviewer
CMS / content-platform pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off SEO + a11y + content-policy decisions before senior-dev claims tasks.
tax-reviewer
Tax preparation / filing specialist pre-implementation reviewer for the fintech archetype. Outputs threat model TM-tax-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.
voice-ai-reviewer
Voice-AI / telephony pre-implementation reviewer. Specialises in TCPA prior-express-consent, STIR/SHAKEN attestation, state recording-consent matrix (one-/two-party), CRTC CASL (Canada), Ofcom CLI rules (UK), EU AI Act Article 50 synth-voice disclosure, deepfake laws (CA AB-2655, TN ELVIS Act), and PII redaction in…