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 tomzx/agents --skill create-test-skillgit clone --depth 1 https://github.com/tomzx/agentsWrote 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/tomzx/agents/create-test-skill)<a href="https://agentmods.dev/skills/tomzx/agents/create-test-skill"><img src="https://agentmods.dev/badge/skills/tomzx/agents/create-test-skill/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/tomzx/agents/create-test-skill"><img src="https://agentmods.dev/badge/skills/tomzx/agents/create-test-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00123 | $0.07237 |
| Opus 5.5 | $0.00049 | $0.02895 |
| Sonnet 5.5 | $0.00025 | $0.01447 |
| Haiku 4.5 | $0.00012 | $0.00724 |
Grade A, and why
create-test-skill 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.
How it starts
The opening of the file, as written. The whole thing — 520 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Test Skill
Generates a project-specific skill that runs the project's test suites and writes a trace of what it ran.
The generated skill answers four questions for its project: which test levels exist, how each one is set up, which exact command runs it, and whether an agent or a person runs it. Every run also writes a trace document listing the commands called, their results, and any temporary change made to get the tests to execute.
The trace is the point. An agent can make a suite look green by running one narrow test, relaxing an assertion, mocking the code under test, or skipping the slow part. The trace makes those moves visible, so a reviewer can decide in a couple of minutes whether a green result proves what it claims. That intent is written into the generated skill, not just into this one, so it survives after this generation session is gone.
Prerequisites
- Working directory is the project root, or the project is the current repository.
- Read
AGENTS.md,CLAUDE.md,CONTRIBUTING.md,README.md, and.sdlc/context/infrastructure.mdwhen present, since they often name the test commands and the environment. - Permission to install project dependencies and start local services.
- A working copy, not a read-only or detached checkout, because most levels need to write build outputs, caches, or a local database.
- Ask the user before any step that: runs a level expected to take more than 10 minutes, contacts a non-local host, resets or migrates a database that is not obviously disposable, or downloads a large toolchain.
Scope
This skill owns test discovery, environment setup, execution, and the run trace for one project. It writes a project-specific test skill and proves that the skill's commands work.
It does not write tests, review assertions, or fix failing code. A failing suite is recorded as found, because the generated skill must describe the project as it is.
Steps
1. Resolve the project and the generated skill name
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.
- 3d ago First seen · 520 lines · 123 tokens per session scan A 658220a2f39b
create-test-skill is a skill published in the GitHub repository tomzx/agents (13 stars, last pushed yesterday), licensed MIT. It adds 123 tokens to every session and 7,237 once invoked, about $0.0005 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 2026-10-27.
Other skills, from other repositories
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
axiom-testing
Use when writing ANY test, debugging flaky tests, making tests faster, or choosing Swift Testing vs XCTest. Covers unit tests, UI tests, async testing, test architecture.
testing-blocks
Use this when you have made AEM Edge Delivery Services code changes to blocks, scripts, or styles and need to validate them before opening a pull request. Covers unit testing for utilities and logic, browser testing with Playwright, linting, and guidance on what to test and how.
designing-tests
Designs and implements testing strategies for any codebase. Use when adding tests, improving coverage, setting up testing infrastructure, debugging test failures, or when asked about unit tests, integration tests, or E2E testing.
test-automation-expert
Comprehensive test automation specialist covering unit, integration, and E2E testing strategies. Expert in Jest, Vitest, Playwright, Cypress, pytest, and modern testing frameworks. Guides test pyramid design, coverage optimization, flaky test detection, and CI/CD integration. Activate on 'test strategy', 'unit tests'…
JMeter Load Testing
Load and performance testing skill using Apache JMeter, covering test plans, thread groups, assertions, listeners, timers, and distributed testing.