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/junghwayang/oh-my-codex/agents-mdgit clone --depth 1 https://github.com/junghwaYang/oh-my-codexWhat 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 | $0.00622 | $0.00622 |
| Opus 5 | $0.00311 | $0.00311 |
| Sonnet 5 | $0.00124 | $0.00124 |
| Haiku 4.5 | $0.00062 | $0.00062 |
Grade C, and why
oh-my-codex AGENTS.md scanned grade C with 1 finding 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 3d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- Your custom instructions here --> How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - Oh My Codex
This file is automatically loaded by Codex CLI and defines how the multi-agent orchestration works.
Quick Start
Use mode keywords to activate different execution strategies:
| Keyword | Mode | Description |
|---|---|---|
autopilot: |
Full orchestration | PM → Architect → Specialists → QA |
ulw: / ultrawork: |
Parallel execution | Decompose & run in parallel |
plan: |
Planning only | Generate detailed plan without execution |
eco: |
Token-efficient | Use smaller model for simple tasks |
ralph: |
Never give up | Maximum effort with retries |
tdd: |
Test-driven | Write tests first, then implement |
review: |
Code review | Analyze and suggest improvements |
Examples
# Full orchestration
omx "autopilot: build a REST API for user management"
# Parallel execution
omx "ulw: refactor all utility functions"
# Planning only
omx "plan: design a microservices architecture"
# Quick fix (token-efficient)
omx "eco: fix the typo in README"
Agent Roles
When using orchestrated modes, Oh My Codex deploys specialized agents:
Core Agents
- PM (Project Manager) - Coordinates workflow, tracks progress
- Architect - Designs system structure and patterns
- Executor - Implements code changes
Specialists
- Frontend - React, Vue, CSS, UI/UX
- Backend - APIs, databases, server logic
- DevOps - CI/CD, deployment, infrastructure
- QA - Testing, validation, quality assurance
Support
- Analyst - Requirements analysis, documentation
- Researcher - Investigation, best practices
- Debugger - Error diagnosis, fixes
Model Routing
Tasks are automatically routed to appropriate models:
| Complexity | Model | Use Case |
|---|---|---|
| Real-time | gpt-5.3-codex-spark | Simple queries, 1000+ tok/s |
| Simple | gpt-5-codex-mini | Quick fixes, eco mode |
| Standard | gpt-5.2-codex | Default, balanced |
| Complex | gpt-5.3-codex | Autopilot, architecture |
| Maximum | gpt-5.1-codex-max | Ralph, long-running tasks |
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.
- 3d ago First seen · 85 lines · 622 tokens per session scan C 947b80d9264f
oh-my-codex AGENTS.md is an instructions file published in the GitHub repository junghwaYang/oh-my-codex (5 stars, last pushed 6mo ago), licensed MIT. It adds 622 tokens to every session, about $0.0031 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.