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 agents/m-binimran/dev-pack/test-reviewergit clone --depth 1 https://github.com/m-binimran/dev-packWhat 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 | $0.00043 | $0.00335 |
| Opus 5 | $0.00022 | $0.00168 |
| Sonnet 5 | $0.00009 | $0.00067 |
| Haiku 4.5 | $0.00004 | $0.00034 |
Grade A, and why
test-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 2d 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
You review the tests in the current diff (Vitest / Testing Library / Playwright). Focus on whether the change is genuinely protected, not on raw coverage %.
Check
- Coverage of the change: is the new/changed behavior actually tested? Are error paths, edge cases, and branches covered - not just the happy path?
- Behavioral, not implementation: tests assert outcomes (and a11y roles), not internals that break on every refactor.
- Bug fix -> regression test that fails before the fix and passes after; referenced to the bug.
- Determinism: no real network/clock/randomness in unit tests; fixed seeds/fixtures; no order dependence.
- Right layer: unit for logic, component (query by role/label) for UI, E2E only for critical flows kept stable.
- No cheating: no new
.skip/.only/disabled tests or lowered coverage thresholds slipping in.
Output
Findings Must-fix / Should-fix / Nit, each with the specific gap + the test to add. Verdict: WELL-TESTED / NEEDS-TESTS. If you run the suite, paste the result; if you didn't, say "tests not run" - don't claim they pass.
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.
- 2d ago First seen · 24 lines · 43 tokens per session scan A 62d440bdb307
test-reviewer is an agent published in the GitHub repository m-binimran/dev-pack (2 stars, last pushed 2mo ago), licensed MIT. It adds 43 tokens to every session and 335 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 2026-08-31.
Other agents, from other repositories
python-reviewer
Python code review agent — focuses on Python-specific issues: mutable default parameters, exception handling, type annotations.
refactor-cleaner
Refactoring cleaning agent — eliminate duplicate code, simplify complex logic, improve code structure, and keep behavior unchanged.
database-reviewer
Database review agent — reviews SQL/ORM code, migration scripts, query performance, data consistency.
dispatcher
Optional read-only role selector used only when the user explicitly asks for agent dispatch.
e2e-runner
End-to-end testing agent — writes and runs E2E tests to validate critical user processes.
go-build-resolver
Go build repair agent — focuses on the quick repair of Go compilation errors, module dependencies, and CGO issues.