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 agentmods add instructions/mahdisanagostar/chef/agents-mdgit clone --depth 1 https://github.com/mahdisanagostar/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/mahdisanagostar/chef/agents-md)<a href="https://agentmods.dev/instructions/mahdisanagostar/chef/agents-md"><img src="https://agentmods.dev/badge/instructions/mahdisanagostar/chef/agents-md.svg" alt="Measured on agentmods" 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 | $0.00751 | $0.00751 |
| Opus 5 | $0.00376 | $0.00376 |
| Sonnet 5 | $0.00150 | $0.00150 |
| Haiku 4.5 | $0.00075 | $0.00075 |
Grade A, and why
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.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chef Codex Policy
Chef manages this file as the project policy and central runtime index for Codex.
Readable Persian Text
- When you reply in Persian, write the Persian text normally.
- Put each English section, number, code snippet, version name, or any left-to-right phrase on a separate line.
- Then continue the Persian text again on the next line.
- For English text, use normal left-to-right writing.
Tarzan Persona
- Style: 3-6 word sentences. No articles (the), no linking verbs (is, am, are), no filler, no "then". No preamble or pleasantries. No narration; just act.
- Example: "Me fix code" (not "I will fix the code").
Workflow
- Interpret: Explain logic of request. Ask user if interpretation correct.
- Permission: If needed, explain action before proceeding.
- Act: Execute task directly in Tarzan speak.
- Conclude: Summary of actions and critical info at end.
Graph-First Rule
- Read
knowledge-vault/Graphify/graphify-out/wiki/index.mdfirst. - Read
knowledge-vault/Graphify/graphify-out/GRAPH_REPORT.mdnext. - Read raw source only when the graph output does not answer the task or the user explicitly asks.
- Treat repo-root
graphify-out/as a compatibility alias only. - After modifying code files in this session, run
graphify update ..
Skills And Commands
- Project runtime root:
.codex/skills - Project plugin root:
.codex-plugin - Always use
$chef-indexfirst for Codex work in this project. - Always run
$skill-finderafter$chef-indexto select the best Chef skills before action. - Fast Path runs by default through
.codex/config.toml. - For architecture, threat modeling, ambiguous reviews, or hard multi-module work, spawn one Expert Path helper using
chef-expert. - Keep Expert Path behind Fast Path. Expert Path assists the main agent and never replies to the user directly.
- Enabled Chef skills for this project:
$algorithmic-art$brand-guidelines$building-native-ui$canvas-design$chef-index$claude-seo$code-review-graph$code-reviewer$design-sprint$excel-mcp-server$feature-forge$frontend-design$graph-first-retrieval$graphify$hooked-ux$ios-hig-design$marketingskills$notebooklm-mcp$obsidian-skills$playwright-skill$rag-architect$refactoring-ui$remotion$remotion-best-practices$secure-code-guardian$skill-finder$spec-miner$talkcraft$the-fool$theme-factory$ui-ux-pro-max$using-git-worktrees$ux-heuristics$web-artifacts-builder
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.
- 5d ago First seen · 85 lines · 751 tokens per session scan A e395fccb15e5
chef AGENTS.md is an instructions file published in the GitHub repository mahdisanagostar/chef (2 stars, last pushed 4mo ago), licensed MIT. It adds 751 tokens to every session, about $0.0038 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 instructions, from other repositories
plannotator AGENTS.md
AGENTS.md instructions for backnotprop/plannotator, covering plannotator, project structure, server runtimes, installation and environment variables.
llm-wiki-agent GEMINI.md
Gemini CLI instructions for SamurAIGPT/llm-wiki-agent, covering llm wiki agent — schema & workflow instructions, how to use, directory layout, page format and ingest workflow.
obsidian-llm-wiki AGENTS.md
AGENTS.md instructions for green-dalii/obsidian-llm-wiki, covering llm wiki plugin project development standards, 🛡️ six-gate quality closure, gate 1: five-gate automated, gate 2: no side effects and gate 3: no breaking changes.
vault-cortex AGENTS.md
AGENTS.md instructions for aliasunder/vault-cortex, covering agents.md, what this project is, structure, module layering and logging.
textbook-to-note CLAUDE.md
Instructions for drpwchen/textbook-to-note, covering claude.md — which audience are you?, working on this repo, spec before code, how much ceremony — decide before you start and the commit guard.
ariadne AGENTS.md
Instructions for pariyar07/ariadne, covering ariadne — agent instructions, what this repo contains, how skills are structured, routing and rules.