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 jnMetaCode/skillet --skill test-writinggit clone --depth 1 https://github.com/jnMetaCode/skilletWrote 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/jnmetacode/skillet/test-writing)<a href="https://agentmods.dev/skills/jnmetacode/skillet/test-writing"><img src="https://agentmods.dev/badge/skills/jnmetacode/skillet/test-writing/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/jnmetacode/skillet/test-writing"><img src="https://agentmods.dev/badge/skills/jnmetacode/skillet/test-writing.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 | $0.00043 | $0.00526 |
| Opus 5.5 | $0.00017 | $0.00210 |
| Sonnet 5.5 | $0.00009 | $0.00105 |
| Haiku 4.5 | $0.00004 | $0.00053 |
Grade A, and why
test-writing 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.
What it actually says
test-writing
A test's value is the bug it catches later. Test behavior through the public surface, not implementation details — a good test survives a refactor; a bad one breaks with it.
Procedure
- Match the house style first: open 2–3 existing test files; copy their runner, naming, setup helpers and assertion idioms exactly.
- One behavior per test, named as a claim:
install skips a broken entry and installs the rest— readable as a spec when the suite prints. - Choose cases from the code's branches, not from imagination. Read the
function: every
if, every early return, everycatchis a candidate. Priority order:- the happy path (one test, not five variations)
- each error/edge branch (empty input, missing file, duplicate, too-long, zero/negative, unicode)
- the bug you just fixed (regression test that fails without the fix — verify it actually fails by stashing the fix once)
- Real objects over mocks. Mock only true boundaries (network, clock,
randomness). If a test needs four mocks, the unit is wrong — test one level
higher. For clock/randomness, inject (
now,seed) rather than patching globals. - Make failure diagnosable: assert on specific values, not just
truthiness; add a message when the assertion isn't self-explanatory
(
assert.ok(hit1 >= 0.88, 'ranking change regressed recall')). - Independence: each test builds its own state (tmp dirs via
mkdtemp, fresh fixtures) and cleans up. Order-dependence is a flake factory.
Anti-patterns
- Asserting a function was called instead of what it did.
- Snapshot tests for logic (they assert "nothing changed", not "it's correct").
- Testing private helpers directly — route through the public API.
- A test that can't fail (asserting the mock you just configured).
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 First seen · 45 lines · 43 tokens per session scan A e7ec70cf8a48
test-writing is a skill published in the GitHub repository jnMetaCode/skillet (2 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 526 once invoked, about $0.0002 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
test-driven-development
Writing code with tests first: RED-GREEN-REFACTOR, reproduce bugs as failing tests before fixing, and avoid testing anti-patterns. Use when implementing behaviour, fixing a defect, or asked to add tests.
llm-evaluator
Evaluate LLM outputs systematically using LLM-as-judge, human evaluation frameworks, and regression testing. Use when assessing model quality, comparing models, or preventing quality regression.
rust-testing
Rust testing patterns including unit tests, integration tests, async testing, property-based testing, mocking, and coverage. Follows TDD methodology.
cpp-testing
Use only when writing/updating/fixing C++ tests, configuring GoogleTest/CTest, diagnosing failing or flaky tests, or adding coverage/sanitizers.
resolve-author-fix
Find the root cause, implement a focused fix, and prove behavior with targeted tests and recordings.
test-writer
How to write pytest tests for modules in this workspace. Load whenever you are about to write or extend tests.