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.
npx skills add mgiovani/cc-arsenal --skill test-suitegit clone --depth 1 https://github.com/mgiovani/cc-arsenalWrote 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.
[](https://agentmods.dev/skills/mgiovani/cc-arsenal/test-suite)<a href="https://agentmods.dev/skills/mgiovani/cc-arsenal/test-suite"><img src="https://agentmods.dev/badge/skills/mgiovani/cc-arsenal/test-suite/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.
<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="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00086 | $0.02638 |
| Opus 5.5 | $0.00034 | $0.01055 |
| Sonnet 5.5 | $0.00017 | $0.00528 |
| Haiku 4.5 | $0.00009 | $0.00264 |
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 22d 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.
How it starts
The opening of the file, as written. The whole thing — 210 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:
- Read the source file before writing any test for it.
- Discover the test framework from the project itself (Phase 0) rather than assuming pytest/vitest/jest.
- Match the project's existing test style exactly, down to its fixtures and other conventions.
- Run every generated test: a test that has never executed is unverified.
- Only reference methods and functions that exist in the code you read, along with their real interfaces.
- Every test needs a meaningful assertion, not just "does not throw."
- Target untested code paths; don't duplicate coverage that already exists.
- Any coverage percentage or baseline you report must come from a command you actually ran; the same goes for any file path. 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 (Phase 0), write the tests, run them, done. Don't spin up task 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 the checklist 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: do discovery and gap analysis yourself with Read/Grep/Glob, and write the tests for each module group yourself, one group at a time. The phase structure is the contract; parallelism is just a speedup. All Task, Explore and subagent boilerplate lives in references/subagent-template.md.
What ships with it
4 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.
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.
- 22d ago Changed · -201 lines c5d1bf58de25
- 1mo ago Changed · +11 lines a2a83867cbaa
- 1mo ago Changed · +2 lines 8f562a6272b2
- 1mo ago First seen · 398 lines · 86 tokens per session scan A bdc75fc0805c
test-suite is a skill published in the GitHub repository mgiovani/cc-arsenal (8 stars, last pushed 2d ago), licensed MIT. It adds 86 tokens to every session and 2,638 once invoked, about $0.0003 per session on Opus 5.5. 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.
Other skills, from other repositories
testing-anti-patterns
Reviews test code to identify and fix common testing anti-patterns including flaky tests, over-mocking, brittle assertions, test interdependency, and hidden test logic. Flags bad patterns, explains the specific defect, and provides corrected implementations. Use when reviewing test code, debugging intermittent or…
test-patterns
Applies proven testing patterns — Arrange-Act-Assert (AAA), Given-When-Then, Test Data Builders, Object Mother, parameterized tests, fixtures, spies, and test doubles — to help write maintainable, reliable, and readable test suites. Use when the user asks about writing unit tests, integration tests, or end-to-end…
red-green-refactor
Guides the red-green-refactor TDD workflow: write a failing test first, implement the minimum code to make it pass, then refactor while keeping tests green. Use when a user asks to practice TDD, write tests first, follow red-green-refactor, do test-driven development, write failing tests before code, or phrases like…
test-failure-explorer
Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.