agentmods.dev

codex-chef AGENTS.md

Repository instructions for codex-chef, a starter setup for Codex with installable templates, documentation, validation, and security rules. They also point to the files that define the global Codex setup.

In plain words
What is it for?
Use them when maintaining Codex templates, routing profiles, installation scripts, documentation, or repository validation.
Why use it?
They keep changes focused and reduce the risk of exposing secrets, enabling unsafe commands, or overwriting user files without approval.

Instructions file for CodexOpenCode

6 16d ago A scan 352 tokens original MIT
View the source file ucsahinn/codex-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/ucsahinn/codex-chef/agents-md
Clone the repo
git clone --depth 1 https://github.com/ucsahinn/codex-chef

Made for: Codex, OpenCode.

Per session 352 This file is loaded in full into every session.
When invoked 352 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 $0.00352 $0.00352
Opus 5 $0.00176 $0.00176
Sonnet 5 $0.00070 $0.00070
Haiku 4.5 $0.00035 $0.00035

Measured 2d ago against content hash bbe074421d66, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex-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 2d 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 · 53 lines

What it actually says

Repository Working Agreements

Scope

This repository packages a safe Codex setup starter. Keep edits focused on installable templates, docs, validation, and security guardrails.

For the installable global Codex operating contract, review templates/codex/AGENTS.md and catalog/routing-profiles.json. This root file governs maintenance of this repository only.

Security

  • Never commit secrets, auth files, memory files, sessions, local caches, or machine-specific private paths.
  • Keep authenticated MCP connectors disabled by default.
  • Do not add approval rules that auto-allow destructive commands, credential access, publishing, deployments, releases, or broad shell execution.
  • Do not delete, prune, uninstall, drop, truncate, overwrite, or clean files, directories, dependencies, artifacts, local state, or configuration without explicit user approval. Non-destructive edits and validation may continue.
  • Install scripts must back up overwritten files and must not delete user data.
  • Run npm run validate before reporting the repo as push-ready.

Documentation

  • Keep README.md and README.tr.md aligned.
  • Cite official Codex documentation for current behavior.
  • Prefer concise, copy-pasteable commands.
  • When install behavior changes, update docs/install.md, docs/install.tr.md, and docs/security-model.md.

Verification

Use the narrowest meaningful check first:

npm run validate

Before commit or push:

git status --short
git diff --cached

Use Gitleaks when available:

gitleaks detect --redact --no-banner --no-git --verbose
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. 2d ago First seen · 53 lines · 352 tokens per session scan A bbe074421d66

Subscribe to this mod's changes

codex-chef AGENTS.md is an instructions file published in the GitHub repository ucsahinn/codex-chef (6 stars, last pushed 16d ago), licensed MIT. It adds 352 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 2026-08-31.

agent-skillsai-agentscodexcodex-clideveloper-toolsmcp
Related

Other instructions, from other repositories

apm python.instructions.md

Python development guidelines.

microsoft/apm · 78 tokens

codemap CLAUDE.md

Instructions for JordanCoin/codemap, covering 🛑 stop — run codemap before any task, repo root requirement (critical) and required usage.

JordanCoin/codemap · 372 tokens

OpenMicro AGENTS.md

Instructions for stephenleo/OpenMicro, covering openmicro — project conventions and releases.

stephenleo/OpenMicro · 123 tokens

squarebox CLAUDE.md

Instructions for SquareWaveSystems/squarebox, covering claude.md, agent skills, issue tracker, triage labels and domain docs.

SquareWaveSystems/squarebox · 1,772 tokens

domain-experts CLAUDE.md

Instructions for wonsukchoi/domain-experts, covering domain experts — session bootstrap, non-negotiables when adding or editing roles, dual-graph context policy, mandatory: always follow this order and token usage.

wonsukchoi/domain-experts · 1,300 tokens

academic-writing-toolkit CLAUDE.md

Instructions for yha9806/academic-writing-toolkit, covering academic writing project, project overview, directories, targets and reading constraints.

yha9806/academic-writing-toolkit · 356 tokens