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 reducegit 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/reduce)<a href="https://agentmods.dev/skills/escoffier-labs/skillet/reduce"><img src="https://agentmods.dev/badge/skills/escoffier-labs/skillet/reduce/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/reduce"><img src="https://agentmods.dev/badge/skills/escoffier-labs/skillet/reduce.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 | $0.00079 | $0.01781 |
| Opus 5 | $0.00039 | $0.00890 |
| Sonnet 5 | $0.00016 | $0.00356 |
| Haiku 4.5 | $0.00008 | $0.00178 |
Grade A, and why
reduce 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 9d 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.
This is a copy
98% identical to reduce — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
reduce
A reduction simmers a sauce to drive off the water and concentrate the flavor, and the dish tastes the same, only sharper. You do that to code: boil off the excess, concentrate the intent, and the behavior comes out identical. The cook who reduces too hard scorches the pan and changes the dish; the discipline is knowing when to pull it off the heat.
Core principle: same inputs, same outputs, same side effects, same errors, same public interface, same evaluation order. If the behavior moved, it was not a reduction, it was a rewrite. No behavior-preservation evidence, no applied simplification. Violating the letter of that is violating its spirit.
The behavior lock
Before you change a single line, establish the lock. This is the whole safety story; everything else is taste.
- Pin the scope. Default to the code that recently changed (see Scope). Know exactly which files and functions you are reducing before you start.
- Find the tests that cover it. Run them and confirm they exercise the code you are about to touch. If coverage is thin, write characterization tests first (taste) that capture the current behavior, edge cases included, only when that is safe and in scope. If you cannot lock the behavior with tests, drop to report mode.
- Baseline-verify green. Run the suite and read the output before touching anything. You are proving the starting point, not assuming it.
- Reduce in small steps, one category of simplification at a time (see What to reduce).
- Re-run the same verification after each meaningful change. Evidence in hand before any "behavior unchanged" claim (check). A reduction you did not re-run is a hypothesis.
- Cannot lock it? Switch to report mode or ask the user. Never apply a simplification you cannot prove safe.
Two modes
Apply is the default for recently changed code that has tests, or where characterization tests can be added safely. You make the edits, one category per commit, with the verification evidence.
What ships with it
2 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.
- 9d ago First seen · 110 lines · 79 tokens per session scan A 521238bb4be4
reduce is a skill published in the GitHub repository escoffier-labs/skillet (4 stars, last pushed 8d ago), licensed MIT. It adds 79 tokens to every session and 1,781 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to reduce, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
production-audit
Exhaustive production-readiness audit of any codebase or product. Runs diverse-angle discovery passes until two consecutive passes find nothing new, adversarially verifies every finding against the real code, and reports one flat severity-tagged list with file:line evidence. No summary, no hedging.
craft-audit
The front door to the craft skills — a whole-project production-readiness orchestrator that drives the ten per-domain craft skills (ux, frontend, backend, db, security, infra, observability, testing, lint, ai) instead of auditing one surface at a time. It discovers the project's shape, plans an audit per surface, and…
craft-backend
The Craftsman standard for building and reviewing backend code — API routes, request validation, the authentication boundary, service/business logic, error handling, route rate-limit middleware, third-party integrations, and background jobs. Use this WHENEVER the work touches the server side: adding or reviewing a…
review-work
Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.
one-way-door
Flags irreversible decisions before commit. Use for data models, infra, auth boundaries, API contracts, event schemas, CI/CD.
critical-code-reviewer
Rigorously review code or pull requests for correctness, security, accessibility, maintainability, tests, and edge cases. Use when users request a critical code review, want a guided walkthrough of findings, need implementer-facing feedback, or want to prepare, create, or submit a GitHub pull request review.