test-reviewer

A test-review agent for Vitest, Testing Library, and Playwright tests, covering unit, component, and browser-based end-to-end testing.

In plain words
What is it for?
Use it after code or test changes to review test coverage, accessibility-focused assertions, determinism, test-layer choices, and accidental skipped or weakened tests.
Why use it?
It checks whether tests protect real behaviour, important error cases, bug fixes, and edge cases instead of merely increasing coverage numbers.

Agent

Install

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.

agentmods
npx agentmods add agents/m-binimran/dev-pack/test-reviewer
Clone the repo
git clone --depth 1 https://github.com/m-binimran/dev-pack
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 335 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 2d ago against content hash 62d440bdb307, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

agents/test-reviewer.md · 24 lines

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.

Changes

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.

  1. 2d ago First seen · 24 lines · 43 tokens per session scan A 62d440bdb307

Subscribe to this mod's changes

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.