Borrowing it
Nothing to install: this file belongs to Ducksss/codex-profiles. 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/Ducksss/codex-profiles/main/AGENTS.mdgit clone --depth 1 https://github.com/Ducksss/codex-profilesWrote 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/ducksss/codex-profiles/agents-md)<a href="https://agentmods.dev/instructions/ducksss/codex-profiles/agents-md"><img src="https://agentmods.dev/badge/instructions/ducksss/codex-profiles/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/ducksss/codex-profiles/agents-md"><img src="https://agentmods.dev/badge/instructions/ducksss/codex-profiles/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 | $0.01943 | $0.01943 |
| Opus 5.5 | $0.00777 | $0.00777 |
| Sonnet 5.5 | $0.00389 | $0.00389 |
| Haiku 4.5 | $0.00194 | $0.00194 |
Grade A, and why
codex-profiles 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 13d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI coding agents (Codex, Claude Code, Cursor, and similar) working in this repository. Humans should start with README.md.
agent.mdis the user-facing install and setup guide for agents. Project-internal outreach operations live underops/outreach/.
What this project is
codex-profiles is a single-file, dependency-free Bash CLI for named Codex
homes and named ChatGPT windows with separate local state. Every profile
selects a CODEX_HOME; named macOS Desktop launches additionally select
Electron user data for the entire ChatGPT window across Chat, Work, and Codex.
The whole program is bin/codex-profile.
It is community-maintained and is not an official OpenAI project.
Repository layout
bin/codex-profile— the entire CLI (Bash). Edit this for behavior changes.macos/— optional native menu-bar companion; delegates profile operations to the bundled CLI. Build and DMG programs live inscripts/macos/.raycast/— optional Raycast extension (TypeScript, its own npm dependencies); delegates every profile operation to thecodex-profileCLI (a standalone install or the menu-bar app's bundled copy) and never reads auth data. Background calls use argument lists; Terminal launches pass the user's shell one command whose values are single-quoted so sh, bash, zsh and fish all read them literally (AppleScriptquoted form ofis not fish-safe). It is outside the npm package andmake check; verify it withnpm run typecheck,npm testandnpx prettier --check .insideraycast/.npm run lintfails untilauthorinraycast/package.jsonis a real Raycast username, so usenpx eslint src testuntil then. Its icon renderer isscripts/raycast/render-extension-icon.swift.agent.md— user-facing install and profile-setup instructions for AI agents..agents/skills/— repo-local Codex outreach workflow skills.ops/outreach/— project-internal distribution prompt, launch playbook, and tracker runbook.scripts/check— canonical syntax, test, lint, and full-check dispatcher.scripts/release/— directly tested release-channel programs; workflow YAML only maps permissions, inputs, secrets, and ordering.scripts/aur/— non-pushing AUR preparation and read-only verification.test/— suites grouped bycli,install,packaging,release,site, andoutreach; shared infrastructure lives intest/liband fixtures intest/fixtures.docs/— GitHub Pages site plusllms.txt,robots.txt, andsitemap.xml.Makefile— stable delegates includingcheck,test,lint, install, and package smoke targets.CHANGELOG.md— Keep a Changelog format; add entries under## Unreleased.
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.
- 13d ago Changed · +4 lines · +68 tokens per session 04fa6683f028
- 26d ago Changed · +10 lines · +178 tokens per session c4a7ec627e72
- 1mo ago Changed · +2 lines · +36 tokens per session 3fabf360a056
- 2mo ago Changed · -2 tokens per session 2de843cf46ce
- 2mo ago Changed · +7 lines · +103 tokens per session a75499cbad2c
- 2mo ago First seen · 136 lines · 1,560 tokens per session scan A 8338b41eec7e
codex-profiles AGENTS.md is an instructions file published in the GitHub repository Ducksss/codex-profiles (193 stars, last pushed 3d ago), licensed MIT. It adds 1,943 tokens to every session, about $0.0078 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.
codex-profiles AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| codex-profiles AGENTS.mdDucksss/codex-profiles | Instructions file | 193 | 3d ago | MIT | A | 1,943 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |