agentmods.dev

sous-chef AGENTS.md

sous-chef AGENTS.md is an instructions file for Codex, OpenCode from tomascupr/sous-chef. It costs 353 tokens per session, scanned A, original, MIT.

Project instructions for sous-chef, a Claude Code plugin made mainly from Markdown, JSON, and TOML files. They describe its directory layout, seven skills, templates, Codex profiles, documentation standards, and command conventions.

In plain words
What is it for?
Use them when editing the plugin’s skills, manifests, Codex profiles, templates, documentation, or verification scripts.
Why use it?
They help contributors understand where each part belongs and keep instructions, examples, and supporting research consistent.

Instructions file for CodexOpenCode

not rated 75 1mo ago A scan 353 tokens original MIT
View the source file tomascupr/sous-chef
Install

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.

agentmods
npx agentmods add instructions/tomascupr/sous-chef/agents-md
Clone the repo
git clone --depth 1 https://github.com/tomascupr/sous-chef

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for sous-chef AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tomascupr/sous-chef/agents-md.svg)](https://agentmods.dev/instructions/tomascupr/sous-chef/agents-md)
Your own site
<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="Measured on agentmods" height="20"></a>
Per session 353 This file is loaded in full into every session.
When invoked 353 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00353 $0.00353
Opus 5 $0.00177 $0.00177
Sonnet 5 $0.00071 $0.00071
Haiku 4.5 $0.00035 $0.00035

Measured 5d ago against content hash 9980aad83cd0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 5d 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.

AGENTS.md · 27 lines

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 manifests
  • skills/serve|fire|taste|refire|simmer|mise|receipts/ - the seven skills (each SKILL.md + optional references/)
  • codex/ - Codex-side profiles shipped to ~/.codex/ (default + GLM-via-OpenRouter)
  • templates/ - files /mise scaffolds 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.sh is the executable invariant list - run it before a PR; CI runs the same script on every PR and push to main.
Changes

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.

  1. 5d ago First seen · 27 lines · 353 tokens per session scan A 9980aad83cd0

Subscribe to this mod's changes

sous-chef AGENTS.md is an instructions file published in the GitHub repository tomascupr/sous-chef (75 stars, last pushed 1mo ago), licensed MIT. It adds 353 tokens to every session, about $0.0018 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 2026-08-30.

Building agentsGLMMulti-Agentai-agentsclaude-codecodexloop-engineering
Related

Other instructions, from other repositories

b3rys-team-os CLAUDE.md

Claude Code instructions for b3rys/b3rys-team-os, covering team-collab — project rules, 정체, 핵심 결정 (불변), 디렉토리 규칙 and 작업 규칙.

b3rys/b3rys-team-os · 383 tokens

solo AGENTS.md

AGENTS.md instructions for solo-agent/solo, covering project testing rules and project service lifecycle rules.

solo-agent/solo · 306 tokens

research-os AGENTS.md

Instructions for lxinfei5/research-os, covering researchos — constitution, §0 what this is, §1 directory discipline, §2 half-life (innovation 1) — memory design and §3 behavior pillars (innovations 2–5).

lxinfei5/research-os · 1,143 tokens

AI-System-Design-Consultant CLAUDE.md

Claude Code instructions for deepanshu2711/AI-System-Design-Consultant, covering claude.md, what this is, running it, load-bearing typos — do not "fix" these paths and agent node pattern.

deepanshu2711/AI-System-Design-Consultant · 674 tokens

agent-eve CLAUDE.md

Instructions for shehryarsaroya/agent-eve, covering claude.md — agent eve (né the compact, then agent transfer), 0. 🚨 hard rules, 1. what this is, 2. doc map and 3. state of play (2026-07-26).

shehryarsaroya/agent-eve · 9,010 tokens

team-shinchan AGENTS.md

Instructions for seokan-jeong/team-shinchan, covering agents.md - team-shinchan agent map, layer architecture, agent registry, call flow and quick reference.

seokan-jeong/team-shinchan · 910 tokens