agentmods.dev

codex-claude-code-config AGENTS.md

codex-claude-code-config AGENTS.md is an instructions file for Codex, OpenCode from AnastasiyaW/codex-claude-code-config. It costs 1,938 tokens per session, scanned A, original, MIT.

A set of instructions for AI coding agents working in a configuration repository. It explains the repository’s principles, templates, hooks, skills, rules, and workflows.

In plain words
What is it for?
Setting up an agent-friendly repository, transferring files, applying architecture or security guidance, installing safety hooks, and using reusable instruction bundles.
Why use it?
It gives an agent a clear way to choose and apply project guidance without loading every rule at once.

Instructions file for CodexOpenCode

not rated 147 changed yesterday A scan 1,938 tokens original MIT
View the source file AnastasiyaW/codex-claude-code-config
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/anastasiyaw/codex-claude-code-config/agents-md
Clone the repo
git clone --depth 1 https://github.com/AnastasiyaW/codex-claude-code-config

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 codex-claude-code-config AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/anastasiyaw/codex-claude-code-config/agents-md.svg)](https://agentmods.dev/instructions/anastasiyaw/codex-claude-code-config/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/anastasiyaw/codex-claude-code-config/agents-md"><img src="https://agentmods.dev/badge/instructions/anastasiyaw/codex-claude-code-config/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,938 This file is loaded in full into every session.
When invoked 1,938 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 $0.01938 $0.01938
Opus 5 $0.00969 $0.00969
Sonnet 5 $0.00388 $0.00388
Haiku 4.5 $0.00194 $0.00194

Measured yesterday against content hash 7848fcc77da7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex-claude-code-config 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 yesterday.

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 · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This is a configuration system repository for AI coding agents, not an application. It collects battle-tested architectural principles, security hardening, and decision frameworks that any coding agent can drop into any project.

Purpose

  • principles/ - architectural principles, each preventing a specific failure mode
  • alternatives/ - side-by-side comparisons of 2-5 approaches per problem
  • hooks/ - ready-to-use Python hook scripts (session management, safety guards); installer: scripts/install_hooks.py
  • templates/ - starter CLAUDE.md and REVIEW.md files for different project types
  • skills/ - domain-specific knowledge bundles (loaded on demand)
  • rules/ - drop-in .claude/rules/ files (agent-harness design rules live on-demand in the agent-harness-design skill, not always-on)
  • workflows/ - dynamic-workflow commands + cost lessons
  • scripts/ - utilities (hook installer, config drift validator, KV-cache stats, public-repo sync)
  • CLAUDE.md - Claude Code-specific overlay (extends this file)

How agents should use this repo

When the user asks you to "set up this project" or "apply these principles":

  1. Read README.md first - it maps principles to the problems they solve
  2. Read principles/README.md for the maturity-level map (L1 -> L2 -> L3)
  3. Do NOT bulk-copy everything. Pick what matches the user's actual project:
    • Any project: Principle 09 (Supply Chain Defense), Principle 10 (Agent Security), Principle 11 (Documentation Integrity)
    • Long sessions expected: Principle 07 (Codified Context) + alternatives/context-management.md
    • Long-running project: templates/long-run-project/, a Git worktree with an origin remote, and an agent-facing KB before creating feature_list.json (that marker enables the completion gates)
    • Multi-agent work: Principle 01 (Harness Design) + Principle 06 (Multi-Agent Decomposition)
    • Iterative optimization: Principle 03 (Autoresearch)
  4. Before copying a principle, verify the user's stack matches the examples
  5. After setup, run scripts/validate_config.py --strict and the relevant hook self-tests to catch drift in the freshly assembled config

Read the full file on GitHub · 160 lines

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. yesterday Changed · +15 lines · +228 tokens per session 7848fcc77da7
  2. 5d ago First seen · 145 lines · 1,710 tokens per session scan A a66514e2e290

Subscribe to this mod's changes

codex-claude-code-config AGENTS.md is an instructions file published in the GitHub repository AnastasiyaW/codex-claude-code-config (147 stars, last pushed 2d ago), licensed MIT. It adds 1,938 tokens to every session, about $0.0097 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 agentsLLMagent-harnessai-agentsclaudeclaude-codeharness
Related

Other instructions, from other repositories

learn-harness-engineering CLAUDE.md

Instructions for walkinglabs/learn-harness-engineering, covering claude.md, project overview, commands, documentation site and run lecture code examples.

walkinglabs/learn-harness-engineering · 776 tokens

pydantic-ai AGENTS.md

AGENTS.md instructions for pydantic/pydantic-ai, covering your primary responsibility is to the project and its users, gathering context on the task, ensuring the task is ready for implementation, philosophy and requirements of all contributions.

pydantic/pydantic-ai · 3,618 tokens

ratel AGENTS.md

AGENTS.md instructions for ratel-ai/ratel, covering agents.md — working in the ratel repo, build & test, rust, ts and python (from src/sdk/python/; needs uv).

ratel-ai/ratel · 1,013 tokens

agent-harness-kit AGENTS.md

AGENTS.md instructions for enmanuelmag/agent-harness-kit, covering available research tools, agents.md — @cardor/agent-harness-kit, project, health check (run before making codebase changes) and harness data (source of truth).

enmanuelmag/agent-harness-kit · 929 tokens

san AGENTS.md

AGENTS.md instructions for genai-io/san, covering san agent guide, start here, repository shape, rules and common commands.

genai-io/san · 676 tokens

browser-agent AGENTS.md

Instructions for uiuing/browser-agent, covering agents.md — guide for ai coding agents, setup & commands, tests — run these before claiming done, repository layout and architecture invariants (do not break these).

uiuing/browser-agent · 1,806 tokens