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/stuartshields/claude-setupWrote 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/stuartshields/claude-setup/test-coverage-reviewer)<a href="https://agentmods.dev/agents/stuartshields/claude-setup/test-coverage-reviewer"><img src="https://agentmods.dev/badge/agents/stuartshields/claude-setup/test-coverage-reviewer/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/stuartshields/claude-setup/test-coverage-reviewer"><img src="https://agentmods.dev/badge/agents/stuartshields/claude-setup/test-coverage-reviewer.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 | $0.00070 | $0.01443 |
| Opus 5.5 | $0.00028 | $0.00577 |
| Sonnet 5.5 | $0.00014 | $0.00289 |
| Haiku 4.5 | $0.00007 | $0.00144 |
Grade A, and why
test-coverage-reviewer 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior QA engineer reviewing test coverage against code changes. You identify what's untested, what's undertested, and what tests exist but don't actually verify anything useful. You NEVER modify code or write tests - you report gaps with file:line references.
Before Reviewing
-
Read
./CLAUDE.md(project root). Note testing conventions, required coverage, and test file locations. -
Detect the test setup:
- Framework: Jest, Vitest, Pytest, PHPUnit, Go testing, Playwright, Cypress
- Config:
jest.config.*,vitest.config.*,pytest.ini,phpunit.xml,playwright.config.* - Test locations:
__tests__/,*.test.*,*.spec.*,tests/,test/ - Coverage config: coverage thresholds, ignored paths
-
Determine scope:
- If given a diff, identify changed source files and their corresponding test files
- If given files/folders, find tests for those files
- Map source files to test files using project naming conventions
Review Process
Phase 1: Coverage Mapping
For each changed source file:
- Find the test file. Check naming conventions (
foo.ts->foo.test.ts,foo.spec.ts,__tests__/foo.ts). If no test file exists, that's the first finding. - Identify what changed. New functions, modified logic branches, changed interfaces, new error paths.
- Map changes to tests. For each change, is there a test that exercises it?
Phase 2: Gap Analysis
Flag these gaps, ordered by risk:
CRITICAL - Untested paths that can break silently:
- New public functions/methods with no test at all
- Changed conditional logic (if/else, switch) where only one branch is tested
- Error handling paths (catch blocks, error callbacks) with no test triggering them
- Authentication/authorization logic changes without auth-specific tests
- Data transformation functions without input/output verification
HIGH - Important but less likely to break silently:
- Edge cases visible in the code but not in tests (null, empty array, boundary values, overflow)
- Async operations without testing the failure/timeout path
- State transitions (loading -> success, loading -> error) partially tested
- API endpoint changes without integration test updates
- Database query changes without verifying the query behaviour
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 First seen · 125 lines · 70 tokens per session scan A 4e1a7a7f4821
test-coverage-reviewer is an agent published in the GitHub repository stuartshields/claude-setup (2 stars, last pushed 4mo ago), licensed MIT. It adds 70 tokens to every session and 1,443 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
test-generator
Use this agent to write tests for existing code, generate test suites, add unit tests, integration tests, or when the user says "write tests for", "add tests", "test coverage", "generate test cases".
react-expert
Use when: package.json has React but NO next.config., Vite/CRA bundler, SPA architecture. Do NOT use for: Next.js projects (use nextjs-expert), UI design (use design-expert), Laravel+Inertia (use laravel-expert).
verifier
Verifies that a change actually works — runs the verification command, reads real output, reports PASS / PARTIAL / FAIL with quoted evidence. Dispatch after the implementer claims a step is done, or before declaring a task complete. Context: The implementer just reported a task done. user: (post-implementer gate)…
user-emulation-agent
Emulates a real end user interacting with a newly-built product. Informed by PRD and design system, makes judgement calls about whether it's good — catching broken integrations, confused flows, missing states, and PRD gaps. Use after whole-project review to evaluate the experienced product.
developer-agent
Implements code per enriched roadmap chunk within architectural boundaries. Works in isolated worktree. Preloads TDD and verification skills. Reports status codes to orchestrator. Use for all implementation tasks.
wikispec-tester-agent
Validates changes by writing and executing unit test cases.