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/kivo360/omoios/agents-mdgit clone --depth 1 https://github.com/kivo360/OmoiOSWrote 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/kivo360/omoios/agents-md)<a href="https://agentmods.dev/instructions/kivo360/omoios/agents-md"><img src="https://agentmods.dev/badge/instructions/kivo360/omoios/agents-md.svg" alt="Measured on agentmods" 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 | $0.02214 | $0.02214 |
| Opus 5 | $0.01107 | $0.01107 |
| Sonnet 5 | $0.00443 | $0.00443 |
| Haiku 4.5 | $0.00221 | $0.00221 |
Grade A, and why
OmoiOS 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 5d 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — AI Coding Agent Guide for OmoiOS
This document helps AI coding agents (Claude Code, Cursor, Copilot Workspace, Windsurf, etc.) understand and contribute to OmoiOS efficiently.
What is OmoiOS?
OmoiOS is a spec-driven, multi-agent orchestration system. Users describe a feature, OmoiOS plans it (requirements → design → tasks), executes it with autonomous AI agents in isolated sandboxes, and creates a PR. The core promise: "Start a feature before bed. Wake up to a PR."
Production: Frontend at https://omoios.dev, API at https://api.omoios.dev
Read These First
| Document | Purpose | When to read |
|---|---|---|
| ARCHITECTURE.md | System design, service map, data flow | Before any backend work |
| UI.md | Frontend routes, components, state, design system | Before any frontend work |
| backend/CLAUDE.md | Backend conventions, patterns, anti-patterns | Before writing Python |
| CLAUDE.md | Monorepo structure, dev commands, ports | Always |
| CONTRIBUTING.md | Branch conventions, PR process, testing | Before submitting changes |
| docs/rules/ | Per-mistake rules — tripwires we've already hit (SQLAlchemy session handling, reserved column names, feature flag gotchas) | Before editing dependencies, route handlers, or models |
Repository Map
senior_sandbox/
├── backend/omoi_os/
│ ├── api/
│ │ ├── main.py # FastAPI app + lifespan (25+ services initialized)
│ │ └── routes/ # 38 route files by domain
│ ├── services/ # Business logic (~40 service files)
│ │ ├── models/ # SQLAlchemy 2.0 models (~77 model classes)
│ ├── workers/ # Background workers (orchestrator, sandbox)
│ └── config.py # OmoiBaseSettings (YAML + env)
│
├── backend/config/
│ ├── base.yaml # Default application settings
│ └── test.yaml # Test overrides
│
├── backend/tests/
│ ├── unit/ # Fast isolated tests
│ ├── integration/ # Multi-component tests
│ └── e2e/ # Full workflow tests
│
├── frontend/
│ ├── app/ # Next.js 15 App Router
│ │ ├── (app)/ # Authenticated routes (command, projects, sandboxes, etc.)
│ │ ├── (auth)/ # Login, register, OAuth callback
│ │ └── (dashboard)/ # Root redirect to /command
│ ├── components/
│ │ ├── ui/ # ShadCN primitives (40+) — do not modify
│ │ ├── layout/ # App shell (MainLayout, IconRail, ContextualPanel)
│ │ ├── panels/ # Sidebar panels (route-aware)
│ │ └── {domain}/ # Domain components (command, spec, sandbox, etc.)
│ │ ├── hooks/ # 29 React Query + Zustand hooks (one per domain)
│ ├── lib/api/ # HTTP client + domain-specific API functions
│ └── providers/ # Context providers (Query, Auth, Theme, PostHog)
│
├── subsystems/spec-sandbox/ # Spec execution runtime
├── docs/
│ ├── proposals/ # OmoiOS Improvement Proposals (OIPs)
│ │ ├── page_flows/ # 24 page-by-page UI flow docs
│ ├── user_journey/ # End-to-end user journey docs
│ │ └── architecture/ # 14 system deep-dive docs
└── Justfile # Task runner (just --list for all commands)
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.
- 5d ago First seen · 171 lines · 2,214 tokens per session scan A 38fb1a751b3c
OmoiOS AGENTS.md is an instructions file published in the GitHub repository kivo360/OmoiOS (75 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 2,214 tokens to every session, about $0.0111 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.
Other instructions, from other repositories
archie-hq CLAUDE.md
Claude Code instructions for sweatco/archie-hq, covering claude.md, important, project overview, technology stack and architecture overview.
kungfu copilot-instructions.md
Copilot instructions for kungfu-systems/kungfu: Read and follow AGENTS.md before proposing or running changes. It is the shared agent router for this repository, including the canonical Shifu development and build entrypoint.
autopus-adk GEMINI.md
Gemini CLI instructions for Insajin/autopus-adk, covering autopus-adk harness, 스킬 디렉터리, core guidelines, subagent delegation and file size limit.
nanobot CLAUDE.md
Claude Code instructions for HKUDS/nanobot, a project described as: Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps.
agentic-harness AGENTS.md
AGENTS.md instructions for frangelbarrera/agentic-harness, covering project context, architecture in 30 seconds, non-negotiable rules (from manifesto.md), coding standards and commit conventions.
initrunner CLAUDE.md
Instructions for vladkesler/initrunner, covering initrunner and project map.