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 nortonx/ai-tooling-free --skill create-unit-testsgit clone --depth 1 https://github.com/nortonx/ai-tooling-freeWrote 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/nortonx/ai-tooling-free/create-unit-tests)<a href="https://agentmods.dev/skills/nortonx/ai-tooling-free/create-unit-tests"><img src="https://agentmods.dev/badge/skills/nortonx/ai-tooling-free/create-unit-tests/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/nortonx/ai-tooling-free/create-unit-tests"><img src="https://agentmods.dev/badge/skills/nortonx/ai-tooling-free/create-unit-tests.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 | $0.00031 | $0.01261 |
| Opus 5.5 | $0.00012 | $0.00504 |
| Sonnet 5.5 | $0.00006 | $0.00252 |
| Haiku 4.5 | $0.00003 | $0.00126 |
Grade A, and why
create-unit-tests 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 1mo 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arguments
[<file-path | directory | module>]
- Optional. Scopes test generation to a specific target; default is the branch diff vs
main/master. - Examples:
/create-unit-tests,/create-unit-tests src/payments/
Copilot CLI note:
$ARGUMENTSdoes not substitute in skills; include the argument inline in your prompt.
Create Unit Tests
Act as or delegate to the test automation role to write unit tests for the resolved scope.
Scope
Default: diff between this branch and the base branch (main/master), narrowed to changed functions only. If provided, scope to: $ARGUMENTS (a file path, a directory, or a module name).
Hard rule: never touch files outside the resolved scope. If $ARGUMENTS is empty AND the branch diff is also empty, stop and report: "No changes detected; nothing to test. Pass an explicit target if you want to scope this run manually."
How to write each test
Follow these practices for every test you generate:
- Structure (AAA): Arrange -> Act -> Assert, with a blank line between sections. One logical assertion per test.
- Naming: descriptive:
should_<expected>_when_<condition>orgiven_<state>_when_<action>_then_<outcome>. The name alone should explain the intent. - FIRST:
- Fast: no real network, DB, filesystem, or sleep.
- Independent: no ordering dependencies, no shared mutable state.
- Repeatable: no
time.now, no unseeded random, no env-dependent values. - Self-validating: pass/fail via assertions, not
printor manual inspection. - Timely: written alongside or before the production code, not as an afterthought.
- Mock only at boundaries: external services, filesystem, network, clock, randomness. Do NOT mock the system under test (SUT) or its internal helpers.
- Test behavior, not implementation: assert on public outputs, return values, and observable state; never on private method calls or internal data structures.
- Coverage per changed function:
- Happy path (the documented/obvious case)
- At least one error path
- Boundaries: 0, 1, max, negative
- Nullish / empty inputs
- Collections: empty, single element, ordering
- Target: >=80% branch coverage on the scoped target. (Threshold chosen because below 80% typically leaves entire
catch/error branches untested, the largest source of regressions in this repo's prior bugs. Lower it explicitly with a project-level coverage config if the codebase has a different baseline.)
- Match the repo's existing test style: framework, file location, imports, fixture pattern, assertion library. Mirror what is already there; do not introduce a new style.
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.
- 1mo ago Changed 666aa421de4e
- 1mo ago First seen · 100 lines · 31 tokens per session scan A ad45aeb3f828
create-unit-tests is a skill published in the GitHub repository nortonx/ai-tooling-free (1 stars, last pushed 18d ago), licensed MIT. It adds 31 tokens to every session and 1,261 once invoked, about $0.0001 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-livekit-agents
Writes turn-level tests for a LiveKit agent in the user's normal test suite: pytest (Python) or Vitest (Node.js). Use when the user asks to "write tests for my agent", "add a test for this tool", "test the handoff", "pin this bug", "why does my agent test fail", or after building or changing agent behavior that needs…
squid-testing-python
Write and evaluate effective Python tests using pytest. Use when writing tests, reviewing test code, debugging test failures, or improving test coverage.
refactor
Refactors code for quality and maintainability. Triggers: refactor, clean up, restructure, improve code, modernize.
testing-patterns
Testing strategy: pyramid, AAA, mocks/fakes/stubs, flaky tests, coverage. Triggers: test, fixture, mock, stub, e2e, TDD, Playwright, Cypress, flaky, coverage, property-based.
test-coverage
Use when test coverage falls below target or a new module has no tests — identifies untested code paths and writes targeted unit or integration tests to close the coverage gap.
react-vitest
Use when adding or improving tests in a React project that uses Vitest — covers component testing with Testing Library, mocking hooks, and coverage configuration.