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/sibblegp/odai/agents-mdgit clone --depth 1 https://github.com/sibblegp/ODAIWhat 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 | $0.02722 | $0.02722 |
| Opus 5 | $0.01361 | $0.01361 |
| Sonnet 5 | $0.00544 | $0.00544 |
| Haiku 4.5 | $0.00272 | $0.00272 |
Grade A, and why
ODAI 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 — 365 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ODAI AI Assistant Agents Documentation
Overview
ODAI (ODAI AI Assistant) is a comprehensive AI assistant platform built on FastAPI that orchestrates multiple specialized agents to handle diverse user requests. The system uses OpenAI's Agent framework with a hub-and-spoke architecture where a central orchestrator routes requests to specialized agents.
Architecture
Core Components
- Main Application (
api.py): FastAPI application with WebSocket support - Orchestrator (
connectors/orchestrator.py): Central agent that routes requests - Voice Orchestrator (
connectors/voice_orchestrator.py): Specialized for voice interactions - Individual Agents: Specialized tools for specific services and APIs
- Services Layer: Authentication, chat management, location services
- Firebase Integration: User management, chat history, token tracking
Agent Communication Flow
User Request → WebSocket → Orchestrator → Specialized Agent(s) → Response → User
The orchestrator uses the H.A.N.D.O.F.F. decision framework:
- Has capability: Does the agent solve this task?
- Access: Does it have the right data/API permissions?
- Novelty/Need: Is a tool call necessary vs. known info?
- Delay/Cost: Prefer fewer/cheaper calls if quality unaffected
- Output quality: Will it return the needed format/info?
- Failure fallback: Choose alternates if first likely fails
- Fusion: Orchestrate multiple agents and merge results
Agent Categories
1. Communication & Productivity
- GMail Agent: Email management (send, receive, search, reply)
- Google Calendar Agent: Event scheduling and calendar management
- Google Docs Agent: Document creation, search, and collaboration
- Slack Agent: Team communication integration
- Twilio Assistant: Voice and SMS capabilities
2. Information & Search
- Google Search Agent: Web search functionality
- Google News Agent: News headlines and stories
- Fetch Website Agent: Website content extraction
- Google Shopping Agent: Product search and price comparison
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 · 365 lines · 2,722 tokens per session scan A d8915ed360b3
ODAI AGENTS.md is an instructions file published in the GitHub repository sibblegp/ODAI (21 stars, last pushed 10mo ago), licensed MIT. It adds 2,722 tokens to every session, about $0.0136 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
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.
buildNext
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).
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.
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).
spec-kit 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.
langchain 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.