Borrowing it
Nothing to install: this file belongs to tomascupr/sous-chef. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tomascupr/sous-chef/main/AGENTS.mdgit clone --depth 1 https://github.com/tomascupr/sous-chefWrote 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/instructions/tomascupr/sous-chef/agents-md)<a href="https://agentmods.dev/instructions/tomascupr/sous-chef/agents-md"><img src="https://agentmods.dev/badge/instructions/tomascupr/sous-chef/agents-md/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/instructions/tomascupr/sous-chef/agents-md"><img src="https://agentmods.dev/badge/instructions/tomascupr/sous-chef/agents-md.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 | $0.00353 | $0.00353 |
| Opus 5.5 | $0.00141 | $0.00141 |
| Sonnet 5.5 | $0.00071 | $0.00071 |
| Haiku 4.5 | $0.00035 | $0.00035 |
Grade A, and why
sous-chef AGENTS.md 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 1mo 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.
What it actually says
sous-chef
A Claude Code plugin: Claude (Fable 5) orchestrates and reviews; Codex CLI (GPT-5.6), Claude Sonnet 5, GLM-5.2, or Grok 4.5 implements. This repo is the plugin itself - there is no build step and no code to compile; everything is markdown, JSON, and TOML.
Map
.claude-plugin/- plugin + marketplace manifestsskills/serve|fire|taste|refire|simmer|mise|receipts/- the seven skills (eachSKILL.md+ optionalreferences/)codex/- Codex-side profiles shipped to~/.codex/(default + GLM-via-OpenRouter)templates/- files/misescaffolds into user repos and~/.sous-chef/docs/design.md- research receipts behind every design decision
Working agreements
- Keep SKILL.md bodies short and goal-directed; this plugin targets frontier models - no step-by-step scaffolding a strong model doesn't need.
- Every behavioral claim in docs/design.md must carry a source URL. No uncited claims.
- Command examples must use current syntax: file-per-profile Codex config (>= 0.134),
no
--full-auto, no[profiles.*]tables. - Match the kitchen register lightly - names and taglines, not forced metaphors in instruction text.
scripts/check.shis the executable invariant list - run it before a PR; CI runs the same script on every PR and push to main.
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.
- 1mo ago First seen · 27 lines · 353 tokens per session scan A 9980aad83cd0
sous-chef AGENTS.md is an instructions file published in the GitHub repository tomascupr/sous-chef (76 stars, last pushed 2mo ago), licensed MIT. It adds 353 tokens to every session, about $0.0014 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 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).