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/nathanzane/codex-mobile/agents-mdgit clone --depth 1 https://github.com/NathanZane/codex-mobileWhat 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 | $0.02561 | $0.02561 |
| Opus 5 | $0.01281 | $0.01281 |
| Sonnet 5 | $0.00512 | $0.00512 |
| Haiku 4.5 | $0.00256 | $0.00256 |
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 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.
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:
README.mdnpm run init- 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:
- create or choose a Discord server
- enable Developer Mode and copy the server ID
- create or open the Discord application
- copy the application ID
- create or confirm the bot
- configure server install permissions
- copy the bot token
- invite the bot to the server
- verify bot permissions
- copy the controller user ID
- choose a behavior preset
- save
.envandbridge.config.json - run
npm run doctor - explain how to start and clean up the bridge manually
If The User Says "Set This Up For Me"
Prefer this sequence:
- Read the README sections:
PrerequisitesQuick GuideDetailed GuideStart The BridgeHow It Works In Practice
- Install dependencies with:
npm install
- Guide the user one step at a time instead of dumping the full checklist or asking for all Discord values at once.
- 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.
- 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 addDISCORD_BOT_TOKENdirectly to.envthemselves 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 writebridge.config.json.
- If a value is missing or invalid, ask only for that value again; do not restart the whole checklist.
- Run:
npm run doctor
- If diagnostics pass, do not start the bridge automatically. Tell the user to start it themselves with:
npm start
- When the user uses Codex Desktop, recommend adding this project to the app, opening a chat for this project, and running
npm startthere while they work in other Codex projects. - After the bridge has stopped, recommend
/codex cleanallfrom Discord ornpm run cleanlocally when the user wants to remove bridge-managed Discord channels/threads and local state. - After the user starts the bridge, verify with one or more of:
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.
- 2d ago First seen · 178 lines · 2,561 tokens per session scan A 72a5af2710a5
codex-mobile AGENTS.md is an instructions file published in the GitHub repository NathanZane/codex-mobile (6 stars, last pushed 4mo ago), licensed MIT. It adds 2,561 tokens to every session, about $0.0128 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
codex-provider-sync AGENTS.md
Instructions for Dailin521/codex-provider-sync, covering ai / agent operator guide, vnext architecture baseline, goal, choose the interface and safe operating flow.
codexia AGENTS.md
Instructions for milisp/codexia, covering agents.md, project info, project tech, common commands and project structure.
codex-command-center AGENTS.md
Instructions for sevensir888/codex-command-center, a project described as: A local desktop control center for organizing Codex projects, engineering tasks, sessions, Git changes, Skills, and MCP configuration.
artbot AGENTS.md
Instructions for ArtBlocks/artbot, covering artbot — agent & maintainer guide, what this is, quick commands, two production flags (critical) and architecture (actual).
CodexPotter AGENTS.md
Instructions for breezewish/CodexPotter, covering repository guidelines, workflow principles, engineering rules, core principles: simplicity & readability and better maintainability.
WhatsAppToDiscord AGENTS.md
Instructions for arespawn/WhatsAppToDiscord, covering agent notes (agents.md), project snapshot, fast start, where the source of truth lives and critical guardrails.