test-suite

test-suite is a skill for Claude Code from mgiovani/cc-arsenal. It costs 86 tokens per session (4,320 once invoked), scanned A, original, MIT.

A test-suite generator examines a codebase and creates automated tests for important paths that lack coverage, following the project's existing test framework and style.

In plain words
What is it for?
It identifies the project's test setup, analyzes untested code paths, writes matching tests, and runs the generated tests to verify them.
Why use it?
It helps find and fill testing gaps without assuming a particular language, framework, or test structure.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; mentions subagents; names the AskUserQuestion tool.

Part of the cc-arsenal plugin — 53 skills shipped together

Good fit It identifies the project's test setup, analyzes untested code paths, writes matching tests, and runs the generated tests to verify them.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mgiovani/cc-arsenal/test-suite
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 mgiovani/cc-arsenal --skill test-suite
Clone the repo
git clone --depth 1 https://github.com/mgiovani/cc-arsenal

Made for: Claude Code.

Or install cc-arsenal, the plugin that ships this one along with the rest of its 53 skills.

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-suite

README.md
[![agentmods](https://agentmods.dev/badge/skills/mgiovani/cc-arsenal/test-suite.svg)](https://agentmods.dev/skills/mgiovani/cc-arsenal/test-suite)
Your own site
<a href="https://agentmods.dev/skills/mgiovani/cc-arsenal/test-suite"><img src="https://agentmods.dev/badge/skills/mgiovani/cc-arsenal/test-suite.svg" alt="Measured on agentmods" height="20"></a>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,320 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00086 $0.04320
Opus 5 $0.00043 $0.02160
Sonnet 5 $0.00017 $0.00864
Haiku 4.5 $0.00009 $0.00432

Measured 8d ago against content hash bdc75fc0805c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

test-suite 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 8d 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.

skills/test-suite/SKILL.md · 398 lines

How it starts

The opening of the file, as written. The whole thing — 398 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Suite Generator

Generate comprehensive test suites with coverage gap analysis and parallel test writing, following testing best practices across any project type and framework.

Target

$ARGUMENTS

Anti-Hallucination Guidelines

Test generation must be grounded in code you actually read and patterns you actually verified: a test for a method that doesn't exist, or a coverage number you didn't measure, is worse than no test at all:

  1. Read the source file before writing any test for it.
  2. Discover the test framework from the project itself (Step 0.2) rather than assuming pytest/vitest/jest.
  3. Match the project's existing test style, fixtures, and conventions exactly.
  4. Run every generated test: a test that has never executed is unverified.
  5. Only reference methods, functions, and interfaces that exist in the code you read.
  6. Every test needs a meaningful assertion, not just "does not throw."
  7. Target untested code paths; don't duplicate coverage that already exists.
  8. Any coverage percentage, baseline, or file path you report must come from a command you actually ran, never estimate or invent one, even under time pressure.

A Stop hook re-runs the discovered test/coverage/lint commands automatically before letting the session end (see frontmatter). Phase 4 below exists only to catch failures before that automatic gate fires, not to duplicate it.

Scope: pick a track before starting

  • Small (1-2 tests, a single file, a quick fix): skip task creation and the approval gate. Discover the test command (Step 0.2), write the tests, run them, done. Don't spin up Task Management ceremony for a two-test add.
  • Large (multiple files/modules, a coverage push, anything needing parallel subagents): use the full Phase 0-5 workflow with Task Management below.

If unsure, default to Small and escalate only if the target turns out to span several modules.

Portability: No Task/TaskCreate tools in this environment? Skip task tracking and the parallel subagent fan-out in Phase 3: write the tests for each module group yourself, one group at a time. The phase structure is the contract; parallelism is just a speedup.

Read the full file on GitHub · 398 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 398 lines · 86 tokens per session scan A bdc75fc0805c

Subscribe to this mod's changes

test-suite is a skill published in the GitHub repository mgiovani/cc-arsenal (7 stars, last pushed 8d ago), licensed MIT. It adds 86 tokens to every session and 4,320 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 2026-08-31.

Related

Other skills, from other repositories