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 stagiairegit 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/stagiaire)<a href="https://agentmods.dev/skills/escoffier-labs/skillet/stagiaire"><img src="https://agentmods.dev/badge/skills/escoffier-labs/skillet/stagiaire/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/stagiaire"><img src="https://agentmods.dev/badge/skills/escoffier-labs/skillet/stagiaire.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 | $0.00133 | $0.01968 |
| Opus 5 | $0.00067 | $0.00984 |
| Sonnet 5 | $0.00027 | $0.00394 |
| Haiku 4.5 | $0.00013 | $0.00197 |
Grade A, and why
stagiaire 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 11d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
stagiaire
A stagiaire is a cook visiting from another kitchen. This skill dispatches one-shot workers on other vendors' CLIs: the user's own logins, one model call per dispatch, no API keys, no framework. Each invocation below is the exact argv that works headless, including the flag that stops that CLI from silently doing nothing.
Precondition: the CLI must already be installed and authenticated by the user. Never run a login flow, never touch auth files, never fall back to an API key. If a CLI is missing or logged out, report it and move on to the vendors that work.
The dispatch table
Run these with the task text substituted. Every one returns the worker's answer on stdout.
| Vendor / model | Write-capable dispatch | Read-only dispatch |
|---|---|---|
| Cursor (composer, grok, gpt, claude families) | cursor-agent --model <id> -p --output-format text -f "<task>" |
same with --mode plan --trust instead of -f |
| Grok CLI (grok.com login) | grok -m grok-4.5 -p "<task>" --always-approve |
grok -m grok-4.5 -p "<task>" --permission-mode plan |
| Codex (ChatGPT login) | codex exec --sandbox workspace-write -m <model> "<task>" |
codex exec --sandbox read-only -m <model> "<task>" |
| Claude Code | claude --model <id> --permission-mode bypassPermissions -p "<task>" |
claude --model <id> -p "<task>" (plain -p cannot edit files) |
| Antigravity (Google login) | agy --model "<display name>" --add-dir <dir> --dangerously-skip-permissions --print "<task>" |
agy --model "<display name>" --sandbox --print "<task>" |
| Ollama | ollama run <model> "<task>" |
same (prompt-only, no tools) |
| opencode (ChatGPT login) | opencode run -m <provider>/<model> "<task>" |
same, instruct read-only in the prompt |
| pi (ChatGPT login) | pi --model openai-codex/<model>:<tier> -p "<task>" |
pi --tools read,grep,find,ls --model openai-codex/<model> -p "<task>" |
Model ids: cursor-agent models, agy models, grok models, opencode models, ollama list. Codex reasoning effort is per-run config: codex exec -c model_reasoning_effort=<none|low|medium|high|xhigh> -m <model> "<task>".
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.
- 11d ago First seen · 75 lines · 133 tokens per session scan A 5cc4af3c8ecf
stagiaire is a skill published in the GitHub repository escoffier-labs/skillet (4 stars, last pushed 10d ago), licensed MIT. It adds 133 tokens to every session and 1,968 once invoked, about $0.0007 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 2026-08-31.
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…