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/rizvee/multimodel-dev-os/agents-mdgit clone --depth 1 https://github.com/rizvee/multimodel-dev-osWhat 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 | $0.00602 | $0.00602 |
| Opus 5 | $0.00301 | $0.00301 |
| Sonnet 5 | $0.00120 | $0.00120 |
| Haiku 4.5 | $0.00060 | $0.00060 |
Grade A, and why
multimodel-dev-os 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
Public workspace instruction template for MultiModel Dev OS projects. Tool-specific adapters in
adapters/can reference this file as the shared source of truth. Keep private prompts, transcripts, credentials, and local maintainer notes out of this file.
Project Overview
project: multimodel-dev-os stack: Node.js (ES modules), esbuild, Vitest description: MultiModel Dev OS is a zero-dependency local CLI and developer configuration standard that enforces structure, memory, tasks, and registry safety boundaries for AI coding agents.
Build Commands
build: npm run build (compiles src/ to bin/multimodel-dev-os.js)
test: npm test (runs vitest suites)
verify: node scripts/verify.js (runs strict audit checks)
Coding Conventions
- Language: JavaScript (ES Modules, Node.js native API)
- Framework: Zero runtime dependencies (standard library crypto, fs, path, readline, https, etc.)
- Style guide: Clear JSDoc typing, deterministic canonical serializations, timing-safe crypto
- Type checking: JSDoc type comments
- Formatting: 2-space indentation, single-shebang binary layout
File Structure Rules
src/ -> Application source code
bin/ -> Standalone built binary (do not edit bin/ directly; edit src/)
tests/ -> Unit test files and mock fixtures
docs/ -> Developer manuals and architecture documentation
scripts/ -> Packaging, compilation, and validation scripts
Boundaries
no-touch:
- .env
- .env.local
- node_modules/
- package-lock.json (do not manually edit)
- bin/multimodel-dev-os.js (auto-generated by esbuild, modify src/)
- .ai/registry-signing-key (gitignored private key, generate via keygen)
Agent Roles
| Role | Tool | Scope | Permissions |
|---|---|---|---|
| default | any | all files | read + write |
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 · 78 lines · 602 tokens per session scan A eb6c3dc2f23b
multimodel-dev-os AGENTS.md is an instructions file published in the GitHub repository rizvee/multimodel-dev-os (5 stars, last pushed 15d ago), licensed MIT. It adds 602 tokens to every session, about $0.0030 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
agents AGENTS.md
AGENTS.md instructions for wshobson/agents, covering claude-agents — multi-harness agentic plugin marketplace, map, working in this repo, quality gates (run these before pushing) and regenerating per-harness artifacts.
oh-my-opencode-slim AGENTS.md
AGENTS.md instructions for alvinunreal/oh-my-opencode-slim, covering agent coding guidelines, project overview, commands, code style and general rules.
debroid AGENTS.md
Instructions for PatilShreyas/debroid, covering ai agent contributor guide 🤖, 🎯 intention & motivation, 🏗️ architecture & layers, 1. the core layer (jdi & adb orchestration) and 2. the cli layer (daemon & client).
free-ai-gateway AGENTS.md
Instructions for zaber-dev/free-ai-gateway, covering 🤖 free-ai gateway - agentic development guidelines, 🏛️ monorepo architecture & package boundaries, 🛑 strict architectural rules for agents, 💻 essential developer commands and build all packages across monorepo.
ANWS AGENTS.md
Instructions for Haaaiawd/ANWS, covering agents.md - ai 协作协议, 🧠 30秒恢复协议 (quick recovery), 🗺️ 地图 (领地感知), 🛠️ 工作流注册表 and 📜 宪法 (the constitution).
agents CLAUDE.md
Claude Code instructions for wshobson/agents, a project described as: Multi-harness agentic plugin marketplace for Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, and Google Antigravity.