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 escoffier-labs/skillet --skill trimgit clone --depth 1 https://github.com/escoffier-labs/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/escoffier-labs/skillet/trim)<a href="https://agentmods.dev/skills/escoffier-labs/skillet/trim"><img src="https://agentmods.dev/badge/skills/escoffier-labs/skillet/trim/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/escoffier-labs/skillet/trim"><img src="https://agentmods.dev/badge/skills/escoffier-labs/skillet/trim.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 | $0.00097 | $0.02985 |
| Opus 5.5 | $0.00039 | $0.01194 |
| Sonnet 5.5 | $0.00019 | $0.00597 |
| Haiku 4.5 | $0.00010 | $0.00298 |
Grade A, and why
trim 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
trim
A butcher trims fat so the cut is worth cooking; nobody trims by weight. This skill holds every test to one value bar: a test earns its maintenance cost by protecting behavior, a credible regression, or an independently meaningful contract. Tests that re-assert the source, repeat stronger proof, couple to implementation, or keep test-only production seams alive are fat.
Core principle: optimize for confidence, not deletion count. A deletion without written evidence is a guess, and an uncertain candidate stays.
Three modes, one value bar:
- Authoring gate - every new or changed test, at write time. Runs alongside taste.
- Audit - a focused, read-only-first sweep of one area for junk tests and the seams they demand. Lands as small coherent batches.
- Campaign - prune one whole subsystem's test surface in one pass. Read references/campaign.md before starting one.
Authoring gate
Before adding any test, answer four questions. A missing answer means do not add it yet: redesign the test (a different boundary, a different assertion) until it passes the gate. It never means skipping the test. Under taste, no production code lands until a test passes this gate and fails. If an existing test already fails for the change, that test is the RED step; run it and cite it.
- What does it protect? An observable behavior, invariant, or independent contract.
- What regression makes it fail? Name a credible one.
- Why does existing coverage miss that failure? Each contract has one primary test owner at the strongest boundary. Another layer needs its own distinct risk, such as a transport or lifecycle failure the owner cannot reach. Prefer extending a table-driven case or shared fixture over a near-duplicate test, and consolidate duplicated setup in the refactor step of the same change.
- Does it need a production seam (export, flag, wrapper, injection hook) that no production caller needs? If yes, move the test to the real boundary instead.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · +1 lines 600b0f23cfd2
- 1mo ago First seen · 170 lines · 97 tokens per session scan A 754d91754c24
trim is a skill published in the GitHub repository escoffier-labs/skillet (4 stars, last pushed yesterday), licensed MIT. It adds 97 tokens to every session and 2,985 once invoked, about $0.0004 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 2026-09-25.
Other skills, from other repositories
craft-testing
Craftsman standard for automated testing: strategy, unit/integration/e2e selection, refactor-proof design, flaky tests, mocking boundaries, deterministic data, and merge-gate policy. Use WHENEVER work touches tests: writing/reviewing tests, strategy, "add tests", "why is this flaky", "what should I test", "tests pass…
critique
Adversarial design critique of the current work — render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.
ship
Pre-release gate — run the full gate, responsive + render checks, then produce the release checklist (README badge/current/changelog). Use before tagging a release.
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
browser-test-loop
Use to actually verify a web change in a real browser instead of assuming it works — click through a flow, catch console errors, check a form submits, confirm a fix on the page. Trigger when a UI change needs proof, a bug only reproduces in the browser, or the user asks to test, check, or screenshot the running app.
puppeteer-automation
Expert guidance for browser automation using Puppeteer with best practices for web scraping, testing, screenshot capture, and JavaScript execution in headless Chrome.