agentmods.dev

codex-mobile: Instructions file for Codex

AGENTS.md

codex-mobile AGENTS.md is an instructions file for Codex, OpenCode from NathanZane/codex-mobile. It costs 2,561 tokens per session, scanned A, original, MIT.

Project instructions for codex-mobile, a tool for connecting a Discord bot to Codex. They define the supported platforms and the expected setup process.

In plain words
What is it for?
Use them when setting up, starting, debugging, or cleaning the project, including creating the Discord bot, configuring permissions and credentials, and running the health check.
Why use it?
They keep the README, setup script, and AI-assisted setup aligned, while clarifying that Windows is the main supported platform.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions subagents; mentions AGENTS.md; mentions Codex.

This is NathanZane/codex-mobile's own configuration. It tells Codex and OpenCode how to work on codex-mobile itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything codex-mobile configures →

not rated 5repo 6mo ago A scan 2,561 tokens original MIT
View source ↗ NathanZane/codex-mobile
Reuse

Borrowing it

Nothing to install: this file belongs to NathanZane/codex-mobile. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/NathanZane/codex-mobile/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/NathanZane/codex-mobile

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-mobile AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nathanzane/codex-mobile/agents-md/github.svg)](https://agentmods.dev/instructions/nathanzane/codex-mobile/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/nathanzane/codex-mobile/agents-md"><img src="https://agentmods.dev/badge/instructions/nathanzane/codex-mobile/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.

agentmods 80×15 button for codex-mobile AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/nathanzane/codex-mobile/agents-md"><img src="https://agentmods.dev/badge/instructions/nathanzane/codex-mobile/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,561 This file is loaded in full into every session.
When invoked 2,561 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.02561 $0.02561
Opus 5.5 $0.01024 $0.01024
Sonnet 5.5 $0.00512 $0.00512
Haiku 4.5 $0.00256 $0.00256

Measured 2mo ago against content hash 72a5af2710a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

codex-mobile 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 2mo 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 · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md for codex-mobile

If a user asks you to set up, start, debug, or clean this project, treat README.md as the source of truth for the user-facing flow.

Platform Support

  • Windows is the primary developed and tested platform.
  • macOS is best-effort and not yet validated with Codex Desktop.
  • Linux is unsupported.

Setup Goal

The onboarding story should stay consistent across:

  1. README.md
  2. npm run init
  3. Codex-assisted setup through this AGENTS.md

Do not invent a different setup path unless the user explicitly asks for a manual or advanced route.

Shared Setup Checklist

Use this exact checklist when explaining or guiding setup:

  1. create or choose a Discord server
  2. enable Developer Mode and copy the server ID
  3. create or open the Discord application
  4. copy the application ID
  5. create or confirm the bot
  6. configure server install permissions
  7. copy the bot token
  8. invite the bot to the server
  9. verify bot permissions
  10. copy the controller user ID
  11. choose a behavior preset
  12. save .env and bridge.config.json
  13. run npm run doctor
  14. explain how to start and clean up the bridge manually

If The User Says "Set This Up For Me"

Prefer this sequence:

  1. Read the README sections:
    • Prerequisites
    • Quick Guide
    • Detailed Guide
    • Start The Bridge
    • How It Works In Practice
  2. Install dependencies with:
    • npm install
  3. Guide the user one step at a time instead of dumping the full checklist or asking for all Discord values at once.
  4. For each browser/manual step, explain only the current action, then stop and wait for the user to confirm or paste the one value needed for that step.
  5. Follow this conversational flow:
    • Ask the user to create or choose the Discord server.
    • Ask the user to enable Discord Developer Mode if needed.
    • Ask for the server ID, then save it into .env.
    • Ask the user to create or open the Discord application.
    • Ask for the application ID, then save it into .env.
    • Ask the user to confirm the Bot page exists.
    • Ask the user to configure server install scopes and permissions.
    • Ask for the bot token and save it into .env. Tell the user they may also add DISCORD_BOT_TOKEN directly to .env themselves if they prefer not to paste the token into Codex.
    • Generate or show the invite URL, ask the user to authorize the bot, then verify bot permissions.
    • Ask for the controller user ID and save it into .env.
    • Ask the user to choose the behavior preset, defaulting to recommended, then write bridge.config.json.
  6. If a value is missing or invalid, ask only for that value again; do not restart the whole checklist.
  7. Run:
    • npm run doctor
  8. If diagnostics pass, do not start the bridge automatically. Tell the user to start it themselves with:
    • npm start
  9. When the user uses Codex Desktop, recommend adding this project to the app, opening a chat for this project, and running npm start there while they work in other Codex projects.
  10. After the bridge has stopped, recommend /codex cleanall from Discord or npm run clean locally when the user wants to remove bridge-managed Discord channels/threads and local state.
  11. After the user starts the bridge, verify with one or more of:

Read the full file on GitHub · 178 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. 2mo ago First seen · 178 lines · 2,561 tokens per session scan A 72a5af2710a5

Subscribe to this mod's changes

codex-mobile AGENTS.md is an instructions file published in the GitHub repository NathanZane/codex-mobile (5 stars, last pushed 6mo ago), licensed MIT. It adds 2,561 tokens to every session, about $0.0102 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 2026-08-31.

codexcodex-clicodex-desktopdiscorddiscord-botopenai
Related

codex-mobile AGENTS.md compared with instructions from other repositories

codex-mobile AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
codex-mobile AGENTS.mdNathanZane/codex-mobileInstructions file56mo agoMITA2,561Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode