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 lfyxhappy/lfcode --skill unit-test-engineergit clone --depth 1 https://github.com/lfyxhappy/lfcodeWrote 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/lfyxhappy/lfcode/unit-test-engineer)<a href="https://agentmods.dev/skills/lfyxhappy/lfcode/unit-test-engineer"><img src="https://agentmods.dev/badge/skills/lfyxhappy/lfcode/unit-test-engineer/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/lfyxhappy/lfcode/unit-test-engineer"><img src="https://agentmods.dev/badge/skills/lfyxhappy/lfcode/unit-test-engineer.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 | $0.00058 | $0.00342 |
| Opus 5 | $0.00029 | $0.00171 |
| Sonnet 5 | $0.00012 | $0.00068 |
| Haiku 4.5 | $0.00006 | $0.00034 |
Grade A, and why
unit-test-engineer 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.
What it actually says
Unit Test Engineer
Test a small behavioral boundary without copying its implementation.
Workflow
- Read repository instructions, the target code, existing nearby tests, package scripts, and relevant recent changes.
- State the observable contract: inputs, outputs, errors, side effects, state transitions, and important boundary values.
- Select the narrowest public or stable internal seam. Reuse local test helpers and run the package-local test command before introducing a new pattern.
- Write deterministic cases for normal behavior, invalid input, edge cases, and regression behavior that the code can actually exercise.
- Isolate only nondeterministic or external boundaries. Prefer real values and small fakes over mocks that duplicate implementation details.
- Run the focused test, inspect its assertions and cleanup, then expand to affected package checks when shared behavior changed.
Boundaries
- Keep analysis and a test plan read-only unless the user asks to add or modify tests.
- Do not test private implementation details when callers cannot observe them.
- Do not weaken assertions, add arbitrary waits, suppress errors, or change production behavior solely to make a test pass.
- Do not use production data, credentials, or network calls in a unit test.
Completion Check
Report the behavior covered, cases intentionally excluded, fixture or fake boundaries, changed files if any, and the exact verification commands with their result.
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 · 29 lines · 58 tokens per session scan A 188f0fc48e47
unit-test-engineer is a skill published in the GitHub repository lfyxhappy/lfcode (2 stars, last pushed 6d ago), licensed MIT. It adds 58 tokens to every session and 342 once invoked, about $0.0003 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 2026-09-05.
Other skills, from other repositories
Write tests
Add focused, meaningful tests for code — happy path plus the edge cases that matter.
mandu-testing
Testing patterns for Mandu applications. Use when writing unit tests, integration tests, or E2E tests. Triggers on test, spec, Bun test, Playwright, or testing tasks.
dev-testing
A testing guide that defines when to use unit, integration, API, and end-to-end tests. Unit tests check small pieces of code, while end-to-end tests check a full user flow.
Check work (verify against criteria)
Verify an implementation against acceptance criteria with a reviewer and a tester.
PR babysit (watch & drive to green)
Watch a pull request and delegate fixes until CI is green and reviews are addressed. Requires the GitHub MCP server or gh.
bug-fix
A structured bug-fixing workflow that takes a problem from reproduction and evidence-based cause finding through approval, implementation, testing, and cleanup.