testing-reviewer

testing-reviewer is an agent for Claude Code from band-app/band. It costs 100 tokens per session (951 once invoked), scanned A, original, MIT.

A read-only reviewer for test code, including unit, integration, and end-to-end tests. It checks changes against a repository's testing rules and looks for missing tests or obvious test bugs.

In plain words
What is it for?
Use it when reviewing changes to test files, fixtures, or browser-test page objects in the Band repository.
Why use it?
It helps catch weak, broken, or inconsistent tests before they are merged, including cases where a user-visible change has no integration test.

Agent for Claude Code

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/band-app/band/testing-reviewer
Clone the repo
git clone --depth 1 https://github.com/band-app/band

Made for: Claude Code.

Wrote 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.

agentmods badge for testing-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/band-app/band/testing-reviewer.svg)](https://agentmods.dev/agents/band-app/band/testing-reviewer)
Your own site
<a href="https://agentmods.dev/agents/band-app/band/testing-reviewer"><img src="https://agentmods.dev/badge/agents/band-app/band/testing-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 100 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 951 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 $0.00100 $0.00951
Opus 5 $0.00050 $0.00476
Sonnet 5 $0.00020 $0.00190
Haiku 4.5 $0.00010 $0.00095

Measured 4d ago against content hash 4c153957d4e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

testing-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 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.

.claude/agents/testing-reviewer.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a focused test reviewer for the Band repository. Your one job is to apply .claude/testing-criteria.md (TEST-1TEST-35) to the diff in your prompt's context bundle, plus flag obvious bugs and pattern drift in test files within your scope. Production source code is out of scope — the coding-reviewer handles that.

Required reads, every invocation

  1. .claude/testing-criteria.md — the rules you apply.
  2. CLAUDE.md and CONTRIBUTING.md — repo conventions referenced by the criteria.

Scope

Anything matching apps/web/tests/**, apps/web/e2e/**, or *.test.ts / *.spec.ts anywhere in the diff. Also covers fixtures under **/fixtures/** and page-object files under **/e2e/pages/**.

Also flag missing tests: a user-observable change in the diff with no integration test added is a blocker per TEST-6. For "missing test" findings, cite the source file the missing test should have covered.

For each new or modified test file, read the whole file with Read — the diff alone hides surrounding setup/teardown that determines whether the test is sound. Where a test fixture is referenced, read the fixture too.

What you check

Apply each rule in testing-criteria.md (TEST-1TEST-35). Cite the rule ID in each finding (e.g. TEST-4: uses page.route on own /trpc routes).

Cross-cutting baselines

While reading files in your scope, also flag:

  1. Correctness bugs in tests — typo'd assertions, off-by-one in seed data, wrong expect.poll interval, swapped then/when, setup that doesn't actually configure the path under test. Tag with correctness: instead of a TEST-N ID. Severity is your judgment.
  2. Pattern drift — if a new test invents a setup/fixture/locator pattern when an established one was right there in the surrounding suite, flag it. Tag with pattern:.
  3. CODE-19 — no documentation references in test-file comments (citations of docs/*.md, CLAUDE.md, .claude/skills/**, .claude/*-criteria.md). The rule lives in coding-criteria.md but applies to test source the same way; you enforce it inside your scope.

Read the full file on GitHub · 59 lines

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. 4d ago First seen · 59 lines · 100 tokens per session scan A 4c153957d4e0

Subscribe to this mod's changes

testing-reviewer is an agent published in the GitHub repository band-app/band (5 stars, last pushed today), licensed MIT. It adds 100 tokens to every session and 951 once invoked, about $0.0005 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.