Borrowing it
Nothing to install: this file belongs to saadnvd1/agent-os. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/saadnvd1/agent-os/main/.claude/agents/review-test-quality.mdgit clone --depth 1 https://github.com/saadnvd1/agent-osWrote 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/saadnvd1/agent-os/review-test-quality)<a href="https://agentmods.dev/agents/saadnvd1/agent-os/review-test-quality"><img src="https://agentmods.dev/badge/agents/saadnvd1/agent-os/review-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/saadnvd1/agent-os/review-test-quality"><img src="https://agentmods.dev/badge/agents/saadnvd1/agent-os/review-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 | $0.00069 | $0.01108 |
| Opus 5.5 | $0.00028 | $0.00443 |
| Sonnet 5.5 | $0.00014 | $0.00222 |
| Haiku 4.5 | $0.00007 | $0.00111 |
Grade A, and why
review-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 22d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test quality review
Tests here run under Vitest, locally in a Mac session that inherits AgentOS's environment and in CI on Ubuntu (scripts/check). Flag high-confidence problems in tests and tested code introduced or modified by this branch.
Process
- Changed files: use the list in your prompt. If none was given: with a PR number,
gh pr diff <NUMBER> --name-only; otherwisegit diff main...HEAD --name-status -Mplusgit status --short --untracked-files=all. Read new files whole andgit diff main -- <file>for changed ones. Split them into implementation and tests (*.test.ts(x)next to the file). - Read each changed implementation file with its test.
- Where a test's correctness is in doubt, run it (
npx vitest run <file>) and read what it really asserts. Don't edit files to prove a point: other reviewers are reading the same tree. - Check every rule below.
- Report.
Rules
Missing tests for new behaviour
Flag new code with logic and no test: a merge gate, brake or approval path; an auth or trust decision in lib/security/; a parser (PR bodies, worker messages, CLI output, headers); an orchestrator tool; a migration with data movement; a stack or task state transition. Don't flag pure wiring, types, constants, or UI with no condition or handler.
Security and gate tests must cover the refusal A test of a gate, guard or parser that only checks the happy path. Each needs the input that must be refused (missing, malformed, stale, from another workspace, a proxied request on loopback) asserting the refusal, because the failure mode that matters is failing open.
Tests that pass for the wrong reason
- The assertion is on a value the test stubbed (
vi.mockreturns X, the test asserts X). expect(promise).rejectswithoutawait, or an async assertion never awaited: it passes whatever happens.toThrow()with no message match, where the code could throw for another reason (a typo, a missing mock).- An assertion inside a callback or a
.thenthat never runs, or in a loop over an empty array. toBeTruthy()/toBeDefined()where the value matters.- A regex so loose it matches the error for a different gate.
- A test that mocks the module under test, or mocks
@/lib/...code the behaviour depends on when the real thing can run (this repo runs real git repositories and real SQLite in tests; seelib/orchestrator/signoff.test.ts).
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.
- 22d ago First seen · 62 lines · 69 tokens per session scan A b91d39795e1e
review-test-quality is an agent published in the GitHub repository saadnvd1/agent-os (11 stars, last pushed today), licensed MIT. It adds 69 tokens to every session and 1,108 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 2026-10-07.
Other agents, from other repositories
Test Coverage
Ensure new functionality includes corresponding tests.
Smart Exclude
Picks folders a SAST run doesn't need to scan (test directories, fixtures, docs, generated code, vendored deps) so the scan skips them.
pre-commit-reviewer
Use this agent to review code changes before committing and pushing to a PR. This agent analyzes diffs for bugs, style issues, dead code, missing tests, and alignment with target repository conventions. Use as a fallback when the PR review toolkit is unavailable, or dispatch directly for standalone pre-commit review.…
Test
Scenario-based QA agent. Designs and executes acceptance tests from criteria and implementation. Reports pass/fail with evidence — never fixes code.
Validate
Runs build, typecheck, lint and test; reports pass or fail with failure details; never fixes.
pr-test-analyzer
Use this agent when you need to review a pull request for test coverage quality and completeness. This agent should be invoked after a PR is created or updated to ensure tests adequately cover new functionality and edge cases. Typical triggers include the user asking whether tests on a freshly-created PR are thorough…