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 patriceckhart/zot --skill test-fixgit clone --depth 1 https://github.com/patriceckhart/zotWrote 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/patriceckhart/zot/test-fix)<a href="https://agentmods.dev/skills/patriceckhart/zot/test-fix"><img src="https://agentmods.dev/badge/skills/patriceckhart/zot/test-fix/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/patriceckhart/zot/test-fix"><img src="https://agentmods.dev/badge/skills/patriceckhart/zot/test-fix.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 | $0.00017 | $0.00329 |
| Opus 5 | $0.00009 | $0.00164 |
| Sonnet 5 | $0.00003 | $0.00066 |
| Haiku 4.5 | $0.00002 | $0.00033 |
Grade A, and why
test-fix 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 10d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- test-fix — 100% identical, 0 lines differ
What it actually says
Test fix
When the user reports a failing test (or a test suite failure), work in this order. Resist the temptation to rewrite large chunks of code.
1. Reproduce
Run the failing test in isolation first. For Go: go test -run TestThing ./pkg/.... For Node: npm test -- --run TestThing. The
goal is a fast feedback loop, not the whole suite.
2. Read the failure carefully
- What was expected vs got?
- Which line of test code triggered the failure?
- Is it a logic error in the implementation, an outdated test expectation, or environmental drift (e.g. timezone, locale, file system case-sensitivity)?
3. Choose the smallest possible fix
- If the test is wrong → update the assertion only. Don't restructure.
- If the implementation is wrong → patch the smallest function that fixes the failing case. Avoid drive-by refactors.
- If the test depends on behaviour you need to change deliberately → ask the user before changing the assertion.
4. Re-run
The same isolated test, then the immediate suite, then the full test command if applicable. Stop the moment you see green; don't keep poking.
5. Report
Write 2–3 sentences: what was wrong, what changed, and which command verifies the fix. Include the diff inline.
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.
- 10d ago First seen · 44 lines · 17 tokens per session scan A d7190ae93b97
test-fix is a skill published in the GitHub repository patriceckhart/zot (335 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 329 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
cw-dogfood
Use when a Codewhale change needs proving in the real product, or when asked to build/install/dogfood the local binaries: stamped release build, atomic install, fresh-shell verification, and the manual QA that gates cannot cover.
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.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
rust-check
Run cargo check on the current Rust project to find compile errors.
debug
Reproduce, minimize, localize, identify root cause, and distinguish diagnosis from an authorized fix. Prefer root-cause over symptom patches.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.