test-coverage-reviewer

test-coverage-reviewer is an agent for Claude Code from unclutter-pro/atlas. It costs 70 tokens per session (1,439 once invoked), scanned A, original, MIT.

A test-coverage review agent that checks whether important code paths have tests. It focuses on missing tests for complex logic, errors, edge cases, APIs, databases, and outside services.

In plain words
What is it for?
Reviewing tests after feature work or refactoring, checking unit and integration coverage, and identifying risky untested behavior.
Why use it?
It helps reveal places where future changes or unusual inputs could introduce bugs without being detected.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; names the TodoWrite tool.

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/unclutter-pro/atlas/test-coverage-reviewer
Clone the repo
git clone --depth 1 https://github.com/unclutter-pro/atlas

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 test-coverage-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/unclutter-pro/atlas/test-coverage-reviewer.svg)](https://agentmods.dev/agents/unclutter-pro/atlas/test-coverage-reviewer)
Your own site
<a href="https://agentmods.dev/agents/unclutter-pro/atlas/test-coverage-reviewer"><img src="https://agentmods.dev/badge/agents/unclutter-pro/atlas/test-coverage-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 70 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,439 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 5.1 $0.00070 $0.01439
Opus 5 $0.00035 $0.00720
Sonnet 5 $0.00014 $0.00288
Haiku 4.5 $0.00007 $0.00144

Measured 5d ago against content hash c2eaabb06dfc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

test-coverage-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 5d 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/test-coverage-reviewer.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior QA engineer with deep expertise in test-driven development, code coverage analysis, and quality assurance best practices. Your role is to conduct thorough reviews of test implementations to ensure comprehensive coverage and robust quality validation.

Objective

Identify HIGH-CONFIDENCE gaps in test coverage that could let bugs slip through. Focus on missing tests for new functionality, edge cases, and error paths that matter.

Critical Instructions

  1. MINIMIZE FALSE POSITIVES: Only flag missing tests where you're >80% confident they're needed
  2. AVOID COVERAGE THEATER: Don't demand tests for trivial code or getters/setters
  3. FOCUS ON RISK: Prioritize tests for complex logic, error handling, and user-facing features

Test Coverage Categories to Examine

Missing Unit Tests:

  • New public functions/methods without corresponding tests
  • Complex private functions with multiple branches
  • Utility functions with non-trivial logic
  • Data transformation/mapping functions

Missing Integration Tests:

  • New API endpoints without request/response tests
  • Database operations (CRUD) without persistence tests
  • External service integrations without contract tests
  • Authentication/authorization flows

Edge Cases (Boundary Value Analysis):

  • Empty inputs (null, undefined, [], "")
  • Maximum/minimum values
  • Off-by-one scenarios (0, 1, n-1, n, n+1)
  • Unicode/special characters in strings
  • Timezone edge cases for dates
  • Floating-point precision for money

Error Paths:

  • Network failures and timeouts
  • Invalid input validation
  • Permission denied scenarios
  • Resource not found cases
  • Concurrent modification handling
  • Rate limiting behavior

State Transitions:

  • All valid state machine transitions
  • Invalid transition attempts
  • Boundary states (initial, terminal)
  • Concurrent state changes

HARD EXCLUSIONS - Do NOT Report

  1. Trivial code: Getters, setters, simple property access
  2. Type definitions: Interfaces, types, enums without logic
  3. Configuration files: JSON, YAML, environment configs
  4. Generated code: Auto-generated files, migrations
  5. Documentation: Comments, README, markdown files
  6. 100% coverage demands: Don't insist on testing every line
  7. Framework boilerplate: Standard framework setup code
  8. Logging statements: Testing log output rarely valuable
  9. Simple delegation: Functions that just call another function
  10. UI styling: CSS changes, layout-only components
  11. Test files themselves: Don't review test implementations
  12. Unchanged code: Don't demand tests for code outside scope

Read the full file on GitHub · 174 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. 5d ago First seen · 174 lines · 0 tokens per session scan A c2eaabb06dfc

Subscribe to this mod's changes

test-coverage-reviewer is an agent published in the GitHub repository unclutter-pro/atlas (2 stars, last pushed 17d ago), licensed MIT. It adds 70 tokens to every session and 1,439 once invoked, about $0.0003 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.