oh-my-subagents: Instructions file for Codex

AGENTS.md

oh-my-subagents AGENTS.md is an instructions file for Codex, OpenCode from ringlochid/oh-my-subagents. It costs 4,737 tokens per session, scanned A, original, MIT.

The main instruction document for Oh My Subagents, a coding-agent runtime designed to coordinate accountable teams of agents.

In plain words
What is it for?
Use it as the authoritative guidance for coding agents working in the ringlochid/oh-my-subagents repository.
Why use it?
It defines the product's purpose, design principles, ownership boundaries, routing, recovery, and documentation rules so agents follow a consistent contract.

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 ringlochid/oh-my-subagents's own configuration. It tells Codex and OpenCode how to work on oh-my-subagents 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 oh-my-subagents configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ringlochid/oh-my-subagents. 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/ringlochid/oh-my-subagents/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/ringlochid/oh-my-subagents

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 oh-my-subagents AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ringlochid/oh-my-subagents/agents-md.svg)](https://agentmods.dev/instructions/ringlochid/oh-my-subagents/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/ringlochid/oh-my-subagents/agents-md"><img src="https://agentmods.dev/badge/instructions/ringlochid/oh-my-subagents/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,737 This file is loaded in full into every session.
When invoked 4,737 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 $0.04737 $0.04737
Opus 5 $0.02368 $0.02368
Sonnet 5 $0.00947 $0.00947
Haiku 4.5 $0.00474 $0.00474

Measured 8d ago against content hash 4d009f2f67fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

oh-my-subagents 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 8d 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 · 330 lines

How it starts

The opening of the file, as written. The whole thing — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Oh My Subagents coding agent contract

Status: Reference

This is the canonical root instruction surface for coding agents in this repo. Keep this file and STYLE.md short, stable, and authoritative. Put extended, example-heavy standards in .agents/standards/. If those standards disagree with this file or STYLE.md, the root files win.

Product purpose

Oh My Subagents is an accountable agent-team runtime for complex work that must remain auditable, reproducible, trackable, and operationally recoverable.

  • controller-owned runtime truth stays separate from provider behavior
  • explicit routing and boundaries beat hidden conversational continuity
  • Task-member, Operator, product, and support/audit lanes stay distinct
  • prompts, Work Plans, loose files, reviews, and observability stay explicit enough to validate and recover

Design philosophy

  • start from the owning product contract and verify the shipped code against it
  • change one ownership seam at a time while preserving controller invariants
  • keep recovery, routing, and ownership rules teachable
  • treat docs, prompts, examples, and gates as implementation inputs
  • keep support observability subordinate to controller truth

Principles

  • do not assume agents know the product concepts, nouns, or rules unless the prompt or docs restate them
  • do not assume hidden transcript memory is sufficient for correctness
  • do not assume cross-system context sharing is robust, cheap, or lossless
  • do not assume filesystem state is canonical runtime truth unless canon says so
  • do not assume repo-local YAML or packaged definition files stay canonical after a controller-owned definition registry exists
  • do not assume validation preview is equivalent to publish-, start-, commit-, or runtime-time legality
  • treat Oh My Subagents as one-process and local-tool-first until canon explicitly adds distributed delivery
  • do not assume retries are safe to replay across queued or distributed delivery
  • do not assume support-state files are authoritative controller truth
  • do not introduce compatibility aliases without an explicit product contract
  • do not assume provider terminal success implies assignment success
  • do not assume missing contract details can be reconstructed safely from nearby code shape
  • keep exact inline-versus-after-return timing and sync/async ownership with the owning subject page

Read the full file on GitHub · 330 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. 8d ago First seen · 330 lines · 4,737 tokens per session scan A 4d009f2f67fb

Subscribe to this mod's changes

oh-my-subagents AGENTS.md is an instructions file published in the GitHub repository ringlochid/oh-my-subagents (98 stars, last pushed 8d ago), licensed MIT. It adds 4,737 tokens to every session, about $0.0237 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.

Related

Other instructions, from other repositories

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens

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.

github/spec-kit · 7,104 tokens