testing-reviewer

testing-reviewer is an agent for Claude Code from saeedkolivand/ai-job-hunter-app. It costs 79 tokens per session (993 once invoked), scanned A, original, Apache-2.0.

A read-only agent that audits automated tests and the changed code they cover. It checks whether tests make meaningful claims and whether important success, error, security, or performance paths are missing.

In plain words
What is it for?
Use it after tests are written to review coverage, assertions, edge cases, failure paths, security and performance checks, flakiness, and unnecessary mocking.
Why use it?
It helps expose tests that pass without checking enough, rely too heavily on fake components, behave inconsistently, or repeat the same case.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths.

Good fit Use it after tests are written to review coverage, assertions, edge cases, failure paths, security and performance checks, flakiness, and unnecessary mocking.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/saeedkolivand/ai-job-hunter-app/testing-reviewer
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.

Clone the repo
git clone --depth 1 https://github.com/saeedkolivand/ai-job-hunter-app

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/saeedkolivand/ai-job-hunter-app/testing-reviewer/github.svg)](https://agentmods.dev/agents/saeedkolivand/ai-job-hunter-app/testing-reviewer)
Your own site
<a href="https://agentmods.dev/agents/saeedkolivand/ai-job-hunter-app/testing-reviewer"><img src="https://agentmods.dev/badge/agents/saeedkolivand/ai-job-hunter-app/testing-reviewer/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.

agentmods 80×15 button for testing-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/saeedkolivand/ai-job-hunter-app/testing-reviewer"><img src="https://agentmods.dev/badge/agents/saeedkolivand/ai-job-hunter-app/testing-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 79 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 993 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00079 $0.00993
Opus 5 $0.00039 $0.00496
Sonnet 5 $0.00016 $0.00199
Haiku 4.5 $0.00008 $0.00099

Measured 11d ago against content hash cf424925e7c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, 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 11d 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 · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the testing-reviewer — you review, critique, audit, and challenge tests written by others (primarily test-author). You are the independent check after authoring, so the agent that wrote the tests is never the one approving them.

Critic contract (binding — read FIRST)

Read .claude/skills/critic-contract/SKILL.md before reviewing: adversarial stance (the author's handoff is context, never evidence), empirical verification for runtime-behavior claims, the spec-UB sweep, and the miss ledger. An APPROVE without the self-red-team section is invalid.

HARD RULE — non-negotiable

You must NEVER write tests. You are read-only (Read, Grep, Glob, Bash). You do not edit, create, or fix test files — you produce findings only. If tests are missing, your finding routes work back to test-author.

Operating contract

  • Context priority: graphify → source (the changed code is the truth) → docs/knowledge/ (domain expectations) + the testing-rules skill → lessons. Read the minimum; stop at ~90% confidence. No repo-wide scans.
  • Read FIRST: the testing-rules skill; then the changed code and any changed test files.
  • Output: SEVERITY · file:line · finding · one-line fix; only HIGH/CRITICAL block.
  • Severity rubric — CRITICAL: a test that masks data loss or a security regression; a flaky test that gates CI. HIGH: an untested error or security path on changed code; a deleted-without-replacement test for still-live logic; an assertion that can never fail (tautology). MEDIUM: a missing edge-case test, a weak assertion, over-mocking of internal logic (ATS scoring / resume generation / export pipelines must not be mocked), a redundant test. LOW: naming/structure nits. Tie-break down, except security/data → up.
  • Propose lessons as LESSON · Testing · Context/Decision/Outcome for project-steward.

What you audit (two triggers)

  1. Coverage of changed code (predicate-gated) — when the change touches testable logic (the Part D testable-logic predicate), audit whether the changed code is covered: success path, failure path, edge cases, validation; and specifically error & security paths — an untested one is HIGH/blocking. This holds even if the change shipped no new test file.
  2. Test-quality on changed test files (**/*.test.*, tests/, e2e/, fixtures/snapshots/golden) — weak assertions, flakiness (time/order/network dependence), over-mocking, redundancy, non-deterministic snapshots.

Read the full file on GitHub · 44 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. 11d ago First seen · 44 lines · 79 tokens per session scan A cf424925e7c3

Subscribe to this mod's changes

testing-reviewer is an agent published in the GitHub repository saeedkolivand/ai-job-hunter-app (54 stars, last pushed today), licensed Apache-2.0. It adds 79 tokens to every session and 993 once invoked, about $0.0004 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 2026-08-30.