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 briefgit 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/brief)<a href="https://agentmods.dev/skills/escoffier-labs/skillet/brief"><img src="https://agentmods.dev/badge/skills/escoffier-labs/skillet/brief/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/brief"><img src="https://agentmods.dev/badge/skills/escoffier-labs/skillet/brief.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 | $0.00080 | $0.01635 |
| Opus 5 | $0.00040 | $0.00817 |
| Sonnet 5 | $0.00016 | $0.00327 |
| Haiku 4.5 | $0.00008 | $0.00163 |
Grade C, and why
brief scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **Destructive actions.** `rm -rf`, force push, schema migration, dropping data: confirm before acting. Safety outranks brevity. How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
brief
Before service the chef briefs the line: what is on, what is 86'd, what changed since yesterday. It is short because everyone is busy and specific because a vague brief gets a dish sent back. It is not a tour of the walk-in. It is what you need to work from, said first.
This skill is that brief applied to an agent's answer. The judgment leads, and the reasoning that supports it stays on screen in a form the reader can skim and reject.
Core principle: an analyst supports the decision and does not prescribe it. Handing over a command makes the decision for the reader. Handing over a judgment, its basis, and the runner-up supports theirs.
Why compression alone fails
The usual fix for a buried answer is to cut everything except the action. That reads fast and quietly removes the reader's ability to disagree. When the only thing on screen is run X, evaluating the call means asking the agent to re-explain what it already decided, so the reader accepts it instead. Repeated across many sessions, that trains dependence rather than judgment.
Reasoning does not have to be long to be auditable. Prose hides reasoning inside sentences. A short labeled block exposes it as a list. Three drivers, a confidence marking, and a named runner-up scan faster than one paragraph and are enough to argue with. Same word budget, restructured.
Two shapes
Which shape fires depends on whether the agent is asserting or reporting. The split is structural on purpose: one template with optional fields invites a confidence marking on an observed test result, which is the exact error this format exists to prevent.
Recommendation shape
Fires when the agent is making a call.
BLUF: <the answer>. <probability term>, confidence <High|Moderate|Low> - <basis, one line>.
Why:
- <driver>
- <driver>
Alternative: <runner-up> - better if <indicator>.
Assuming: <the assumption that flips this if wrong>
Next: <one action, under 2 min>
Two to four drivers, one line each. Assuming is omitted when no load-bearing assumption exists. Next is always present.
What ships with it
4 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.
- 10d ago First seen · 124 lines · 80 tokens per session scan C e0c8a14ec150
brief is a skill published in the GitHub repository escoffier-labs/skillet (4 stars, last pushed 9d ago), licensed MIT. It adds 80 tokens to every session and 1,635 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
assess-interview-candidate
A structured hiring-assessment workflow that turns a candidate's résumé and a job description into reviewable evidence, interview questions, and an offline HTML report for interviewers.
task-clarifier
Deep need-clarification skill. Use only when the user explicitly invokes $task-clarifier. Once activated, keep asking until all three goals are met: the user fully understands their own needs, the AI fully understands the user's needs, and the user confirms the AI's understanding is correct. Do not intervene in task…
user-profile-keeper
Local user-profile maintenance skill for Codex, Claude Code, OpenClaw, OpenCode, and other agent harnesses. Use only when the user explicitly invokes $user-profile-keeper to create, initialize, update, query, correct, delete, export, or audit a local persistent user profile. It can extract durable collaboration…
run-history-skill-builder
Turn a completed task, browser flow, artifact pipeline, failure-recovery trace, or repeatedly refined workflow into a new reusable skill package or a reviewed skill-design plan. Use when the user asks to make a new skill from real run history, extract a reusable workflow from conversation/logs/files, summarize lessons…
run-history-skill-upgrader
Use real run evidence, validation failures, source drift, platform drift, and user feedback to plan and, only after explicit approval, apply structural upgrades to an existing skill. Use when the user asks to improve an existing skill from recent runs, recurring failures, outdated sources, excessive bloat, changed…
session-handoff-prompt
Create a concise continuation prompt that a fresh agent session can paste in to resume a long or degraded session. Use when the user asks for a handoff prompt, restart prompt, continuation prompt, context transfer, fresh-session resume, or a compact summary for opening a new session. Do not use for ordinary summaries…