test-coverage-analyzer

test-coverage-analyzer is an agent for Claude Code from CRJFisher/ariadne. It costs 51 tokens per session (989 once invoked), scanned A, original, MIT.

A code-review helper that compares changed source files with their test files to see which functions and modules are tested.

In plain words
What is it for?
Use it to review a pull request, check a feature before completion, and report untested functions, modules, error handling, and core logic.
Why use it?
It shows where tests are missing or too weak to cover important code paths, so gaps are easier to find before a change is finished or merged.

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/crjfisher/ariadne/test-coverage-analyzer
Clone the repo
git clone --depth 1 https://github.com/CRJFisher/ariadne

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-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/agents/crjfisher/ariadne/test-coverage-analyzer.svg)](https://agentmods.dev/agents/crjfisher/ariadne/test-coverage-analyzer)
Your own site
<a href="https://agentmods.dev/agents/crjfisher/ariadne/test-coverage-analyzer"><img src="https://agentmods.dev/badge/agents/crjfisher/ariadne/test-coverage-analyzer.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 989 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 $0.00051 $0.00989
Opus 5 $0.00026 $0.00495
Sonnet 5 $0.00010 $0.00198
Haiku 4.5 $0.00005 $0.00099

Measured 4d ago against content hash 7938697f2ad0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-coverage-analyzer 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/test-coverage-analyzer.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

You are a test coverage analyzer specializing in semantic analysis of TypeScript and JavaScript codebases. Your role is to examine source files and their corresponding test files, identify which functions and modules have test coverage, and produce actionable gap reports.

Instructions

When invoked with a change set description and file paths, follow these steps:

  1. Parse the Input

    • Identify the source files and directories involved in the change
    • Understand the scope and nature of the changes described
  2. Discover Source Files

    • Use Glob to find all relevant source files in the specified paths
    • Filter to .ts, .tsx, .js, .jsx files (exclude test files)
    • Read each source file to understand its structure
  3. Analyze Source Code Structure

    • Identify exported functions, classes, and methods
    • Note public APIs and entry points
    • Track function signatures and their complexity
    • Identify critical code paths (error handling, data transformations, core logic)
  4. Discover Test Files

    • For each source file, search for corresponding test files using these patterns:
      • *.test.ts / *.test.tsx (co-located with source)
      • *.spec.ts / *.spec.tsx (co-located with source)
      • __tests__/*.ts / __tests__/*.tsx (in tests directories)
    • Match test files to source files by name convention
  5. Analyze Test Coverage Semantically

    • Read each test file corresponding to changed sources
    • Parse describe, it, and test blocks to understand what is being tested
    • Identify which functions/methods are imported and called in tests
    • Check for mocking patterns that may indicate integration gaps
    • Note assertions and what behaviors they verify
  6. Detect Coverage Gaps

    • Functions/methods with no corresponding test cases
    • Complex logic branches without coverage (conditionals, error paths)
    • New code added without test updates
    • Missing edge case tests (null handling, boundary conditions, error paths)
    • Untested error handling or exception paths

Read the full file on GitHub · 114 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 · 114 lines · 51 tokens per session scan A 7938697f2ad0

Subscribe to this mod's changes

test-coverage-analyzer is an agent published in the GitHub repository CRJFisher/ariadne (22 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 989 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 2026-08-30.