Borrowing it
Nothing to install: this file belongs to drujensen/aiagent. 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/drujensen/aiagent/main/.claude/skills/test-review/SKILL.mdgit clone --depth 1 https://github.com/drujensen/aiagentWrote 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/drujensen/aiagent/test-review)<a href="https://agentmods.dev/skills/drujensen/aiagent/test-review"><img src="https://agentmods.dev/badge/skills/drujensen/aiagent/test-review/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/skills/drujensen/aiagent/test-review"><img src="https://agentmods.dev/badge/skills/drujensen/aiagent/test-review.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 | $0.00054 | $0.00518 |
| Opus 5.5 | $0.00022 | $0.00207 |
| Sonnet 5.5 | $0.00011 | $0.00104 |
| Haiku 4.5 | $0.00005 | $0.00052 |
Grade A, and why
test-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 4d 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.
What it actually says
Test Review
Write and review tests for:
Instructions
You are orchestrating a Test Writing and Review cycle for the aiagent project.
Phase 1: Test Writing
- Use the Agent tool with
subagent_type: "tester"to write the tests - Pass it:
- What to test (feature description or list of files changed)
- The refined story's acceptance criteria (if available)
- The tester will:
- Read existing test files in the same packages for style reference
- Write tests using testify (assert + mock)
- Mock only at domain interface boundaries
- Cover happy paths, failure paths, and edge cases
- Run
go test ./... -raceto verify all tests pass
Phase 2: Review
4. Use the Agent tool with subagent_type: "tester-reviewer" to review the tests
5. Pass the tester's output (test files written, coverage results)
6. The reviewer will run go test ./... -cover -race and score against the 6 pillars
Phase 3: Iterate 7. If overall score >= 8/10 (APPROVED): Report the test results and scores 8. If overall score < 8/10 (REVISE):
- Extract Critical Issues from the reviewer
- Send issues back to the tester with specific gaps to fill
- Re-review with the tester-reviewer
- Repeat until APPROVED or 3 iterations maximum
Phase 4: Report 9. Present:
- List of test files written/modified
- Coverage report by package
- Final pillar scores table
- Acceptance criteria coverage: which criteria have tests, which don't
Important
- Maximum 3 review iterations
- The tester WRITES TESTS; the reviewer only READS and SCORES
- Tests must use
t.TempDir()for file-based tests, not hardcoded paths - All tests must pass with
-raceflag
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.
- 4d ago First seen · 54 lines · 54 tokens per session scan A 21e9917411c1
test-review is a skill published in the GitHub repository drujensen/aiagent (5 stars, last pushed 2mo ago), licensed MIT. It adds 54 tokens to every session and 518 once invoked, about $0.0002 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 2026-10-03.
Other skills, from other repositories
test-review
You are an expert DataHub test reviewer. Your role is to evaluate pytest smoke tests against established testing standards, identify issues, and provide actionable feedback.
grade-tests
Assess a curated list of tests and produce a PR-ready table with a primary Pass, Failed, Uncertain, or Not applicable result plus A-F quality detail for every resolved test; Uncertain and Not applicable omit the grade. USE FOR new or modified tests supplied as methods, bodies, file spans, or a bounded PR diff.…
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
brooks-test
Test quality review drawing on twelve classic engineering books — with primary focus on xUnit Test Patterns, The Art of Unit Testing, How Google Tests Software, and Working Effectively with Legacy Code — that diagnoses structural problems in an existing test suite: brittleness, mock abuse, coverage illusions, slow…
dart-mechanical-refactor
DART Mechanical Refactor: perform a behavior-preserving mechanical refactor.
quality-checklist
Validate implementation quality through custom checklists, scoring against constitution standards, specification coverage, and producing remediation recommendations.