test-coverage

test-coverage is a command for Claude Code from dachivadachkoria/claude-code-starter-kit. It costs 13 tokens per session (594 once invoked), scanned A, original, MIT.

A code-review command that measures which parts of a project’s tests run the code and creates tests for uncovered sections.

In plain words
What is it for?
Use it to check coverage in Python, JavaScript or TypeScript, and Go projects, then prioritize and add tests for important missing cases.
Why use it?
It helps find untested lines, functions, error cases, and other risky paths instead of relying on guesswork about test quality.

Command 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 commands/dachivadachkoria/claude-code-starter-kit/test-coverage
Clone the repo
git clone --depth 1 https://github.com/dachivadachkoria/claude-code-starter-kit

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/dachivadachkoria/claude-code-starter-kit/test-coverage.svg)](https://agentmods.dev/commands/dachivadachkoria/claude-code-starter-kit/test-coverage)
Your own site
<a href="https://agentmods.dev/commands/dachivadachkoria/claude-code-starter-kit/test-coverage"><img src="https://agentmods.dev/badge/commands/dachivadachkoria/claude-code-starter-kit/test-coverage.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 594 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 $0.00013 $0.00594
Opus 5 $0.00006 $0.00297
Sonnet 5 $0.00003 $0.00119
Haiku 4.5 $0.00001 $0.00059

Measured 3d ago against content hash d6644e25a356, 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 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 3d 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/commands/test-coverage.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Coverage Analysis & Improvement

Analyze and improve test coverage for: $ARGUMENTS

Execution Flow

Step 1: Run Coverage Analysis

Python:

pytest --cov=src --cov-report=term-missing --cov-report=html tests/

JavaScript/TypeScript:

npm test -- --coverage --coverageReporters=text

Go:

go test -coverprofile=coverage.out ./...
go tool cover -func=coverage.out

Step 2: Parse Coverage Report

Identify:

  • Files with < 80% coverage
  • Specific uncovered lines/functions
  • Critical paths missing tests (error handlers, edge cases)

Step 3: Prioritize by Risk

High Priority (test first):

  1. Public API endpoints
  2. Authentication/authorization logic
  3. Data validation functions
  4. Payment/transaction handlers
  5. Error handling paths

Medium Priority:

  1. Business logic in services
  2. Data transformation utilities
  3. Integration points

Low Priority:

  1. Simple getters/setters
  2. Configuration loading
  3. Logging statements

Step 4: Generate Missing Tests

For each uncovered section:

  1. Understand what the code does
  2. Determine why it might be untested (hard to test? edge case?)
  3. Create appropriate test with proper mocking
  4. Verify the test actually covers the target lines

Step 5: Report

📊 Coverage Report
══════════════════════════════════════
Before: 65%  →  After: 84%  (+19%)

Files Improved:
  ✅ src/auth.py: 45% → 92%
  ✅ src/api/users.py: 70% → 88%
  ⚠️ src/legacy.py: 30% → 45% (needs manual review)

New Tests Created:
  - tests/test_auth.py (8 tests)
  - tests/test_users.py (5 tests)

Remaining Gaps:
  - src/legacy.py:45-67 (complex branching)
  - src/utils.py:12-15 (dead code?)
══════════════════════════════════════

Coverage Targets

Category Target Minimum
Overall 80% 70%
Critical paths 95% 90%
New code 90% 80%
Utilities 70% 60%

Options

/test-coverage - Full analysis and improvement /test-coverage --report - Report only, no changes /test-coverage src/auth.py - Focus on specific file /test-coverage --critical - Only critical paths

Read the full file on GitHub · 101 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. 3d ago First seen · 101 lines · 13 tokens per session scan A d6644e25a356

Subscribe to this mod's changes

test-coverage is a command published in the GitHub repository dachivadachkoria/claude-code-starter-kit (4 stars, last pushed 5mo ago), licensed MIT. It adds 13 tokens to every session and 594 once invoked, about $0.0001 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.