autocoverage

autocoverage is a skill for Claude Code, Codex from fabioc-aloha/Alex_Skill_Mall. It costs 83 tokens per session (14,831 once invoked), scanned C, original, MIT.

A staged method for generating unit tests, which test individual functions or small pieces of code, based on measured coverage gaps.

In plain words
What is it for?
Use it to add tests for uncovered modules, validation failures, exceptions, retries, and other difficult paths.
Why use it?
It keeps test work focused on untested error paths and verifies that coverage actually improves without changing production code.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; mentions AGENTS.md.

Good fit Use it to add tests for uncovered modules, validation failures, exceptions, retries, and other difficult paths.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/fabioc-aloha/alex_skill_mall/autocoverage
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.

Any agent
npx skills add fabioc-aloha/Alex_Skill_Mall --skill autocoverage
Clone the repo
git clone --depth 1 https://github.com/fabioc-aloha/Alex_Skill_Mall

Made for: Claude Code, Codex.

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 autocoverage

README.md
[![agentmods](https://agentmods.dev/badge/skills/fabioc-aloha/alex_skill_mall/autocoverage/github.svg)](https://agentmods.dev/skills/fabioc-aloha/alex_skill_mall/autocoverage)
Your own site
<a href="https://agentmods.dev/skills/fabioc-aloha/alex_skill_mall/autocoverage"><img src="https://agentmods.dev/badge/skills/fabioc-aloha/alex_skill_mall/autocoverage/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 autocoverage

Your own site · 80×15
<a href="https://agentmods.dev/skills/fabioc-aloha/alex_skill_mall/autocoverage"><img src="https://agentmods.dev/badge/skills/fabioc-aloha/alex_skill_mall/autocoverage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 14,831 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00083 $0.14831
Opus 5 $0.00042 $0.07415
Sonnet 5 $0.00017 $0.02966
Haiku 4.5 $0.00008 $0.01483

Measured 8d ago against content hash 7734970d27e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade C, and why

autocoverage scanned grade C with 1 finding 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 8d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/parse-cobertura.ps1, scripts/parse-coverage-text.ps1), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

1. **Clean and build locally** (ALL languages): clean stale build artifacts before building (`dotnet clean`, `cargo clean`, `rm -rf dist/`, `npm run clean`, etc.) to prevent inflated coverage from outdated binaries. Then
plugins/code-quality/autocoverage/skills/autocoverage/SKILL.md · 938 lines

How it starts

The opening of the file, as written. The whole thing — 938 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auto Unit Test Generator

Constraints (apply at ALL stages)

DO:

  • Run until target coverage is reached or all modules are terminal (done/stalled)
  • Use measured coverage gaps as input -- never guess
  • Prioritize exception handlers, error paths, retry logic, validation
  • Build and pass all tests locally before every commit
  • Prove a measured coverage delta each iteration
  • Branch from default integration branch; atomic commits per iteration
  • Stick to verified facts from repo files, commands, and recorded artifacts -- never assume

NEVER:

  • Generate tests on a broken build
  • Test constants, DTOs, constructors, properties, default values, or logging
  • Create a test project in the same folder as an existing project
  • Rename folders, move files, rename projects, or change production code

Skill structure

SKILL.md                        -- Pipeline (this file)
scripts/
  parse-cobertura.ps1           -- Parse Cobertura XML into JSON
  parse-coverage-text.ps1       -- Parse pytest/Jest/Vitest text coverage into JSON
references/
  code-coverage.md              -- Coverage commands, tools, parsing
  test-planning.md              -- Prioritization + plan format
  test-generation.md            -- Code gen rules, framework compat, Moq, metadata
  test-quality.md               -- Anti-patterns, review checklist, quality gate
  test-finalization.md          -- Incorporate feedback, produce final code
  ci-pipeline-checklist.md      -- PR/pipeline readiness
  skill-templates.md            -- Reusable output templates
  pr-description-template.md    -- Final PR description template

Reference Lookup

Load the reference file(s) when entering the listed stage.

Stage Reference file(s)
2, 7 code-coverage.md
3 test-planning.md
4 test-generation.md, test-quality.md
5 test-quality.md, test-finalization.md
7 (PR) pr-description-template.md
Pre-PR test-quality.md, test-finalization.md
CI ci-pipeline-checklist.md
any skill-templates.md

Read the full file on GitHub · 938 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. 8d ago First seen · 938 lines · 83 tokens per session scan C 7734970d27e2

Subscribe to this mod's changes

autocoverage is a skill published in the GitHub repository fabioc-aloha/Alex_Skill_Mall (4 stars, last pushed yesterday), licensed MIT. It adds 83 tokens to every session and 14,831 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

flutter-bloc-state-management

Implement BLoC/Cubit state, events, transitions, and async concurrency in Flutter. Use for BLoC/Cubit feature logic, debounced/cancellable events, state rendering, or bloc tests—not generic widget-only work.

HoangNguyen0403/agent-skills-standard · 52 tokens

unit-test

A Go testing workflow for writing unit tests: small tests that check individual functions or components. It supports table-driven cases, where many inputs and expected results are organised in one test, and subtests.

johnqtcg/awesome-skills · 100 tokens

fuzzing-test

A Go testing guide for generating fuzz tests, which repeatedly try varied inputs to find crashes and unexpected behavior. It first checks whether the code is suitable for fuzzing.

johnqtcg/awesome-skills · 74 tokens

test-component

Write React Testing Library tests for an existing component, following the project's RTL conventions (prefer role/label queries, mock at network boundary, no act()). Invoke when the user asks to test, add tests for, or cover a component.

MuhammadUsmanGM/claude-code-best-practices · 50 tokens

adept-writing-tests

How to write tests in the adept Go codebase — table-driven tests with testify, golden fixtures under testdata/, the cmd/adept e2e harness, temp-dir/HOME isolation, and coverage gates. Apply when adding or changing Go tests here. (matches: /test.go).

itaywol/adeptability · 61 tokens

qt-qml-test-run

Builds and runs Qt Quick Test (qmltestrunner / CTest) for a QML project, then writes a Markdown report. Use for "run qml tests", "run qmltestrunner".

TheQtCompanyRnD/agent-skills · 50 tokens