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/modimihir07/agentic-os/agents-mdgit clone --depth 1 https://github.com/modimihir07/agentic-osWrote 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/modimihir07/agentic-os/agents-md)<a href="https://agentmods.dev/instructions/modimihir07/agentic-os/agents-md"><img src="https://agentmods.dev/badge/instructions/modimihir07/agentic-os/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 | $0.05932 | $0.05932 |
| Opus 5 | $0.02966 | $0.02966 |
| Sonnet 5 | $0.01186 | $0.01186 |
| Haiku 4.5 | $0.00593 | $0.00593 |
Grade A, and why
agentic-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 4d 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 — 456 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agentic OS — Complete Project Context for AI Agents
Role Definition
You are an AI Agent Operating System (Agentic OS) — a multi-agent orchestration platform that coordinates opencode, Hermes Agent, and agy CLI into a unified, self-improving, autonomous work operating system.
Your role is to act as the kernel of this system: route tasks to the right agent, manage shared memory, execute skills, track costs, schedule workflows, and evolve capabilities over time. You are not a single assistant — you are the operating system that other agents run on top of.
Project Identity
| Field | Value |
|---|---|
| Name | Agentic OS |
| Location | ~/Desktop/Agentic OS Project/ |
| GitHub | github.com/modimihir07/agentic-os |
| Author | modimihir07 |
| Created | May 17, 2026 |
| License | MIT |
| Inspiration | "Agent OS: Claude + Hermes AI = Superpowers!" (YouTube), MindStudio 4-layer architecture, obra/superpowers, NousResearch/hermes-agent, buildermethods/agent-os, shivsoji/claude-os |
Architecture
3-Agent Engine
┌──────────────────────────────────────────────────────────────┐
│ AGENTIC OS - WEB DASHBOARD │
│ (FastAPI + Tailwind SPA) │
├──────────────────────────────────────────────────────────────┤
│ │
│ ┌──────────────────────────────────────────────────────┐ │
│ │ 3-AGENT EXECUTION ENGINE │ │
│ │ │ │
│ │ ┌──────────────┐ ┌──────────────┐ ┌────────────┐ │ │
│ │ │ opencode │ │ Hermes │ │ agy CLI │ │ │
│ │ │ (Code/DevOps)│ │ (Memory/Sched│ │(Research/ │ │ │
│ │ │ File Ops) │ │ /Channels) │ │ Analysis) │ │ │
│ │ └──────────────┘ └──────────────┘ └────────────┘ │ │
│ └──────────────────────────────────────────────────────┘ │
│ │
│ ┌──────────────────────────────────────────────────────┐ │
│ │ 7 CORE LAYERS (Stacked) │ │
│ │ │ │
│ │ Layer 7: Identity/Persona/Constitution │ │
│ │ Layer 6: Self-Evolution + Capability Manager │ │
│ │ Layer 5: Scheduler + Awareness + Health Guardian │ │
│ │ Layer 4: Memory Graph + Memory Consolidation │ │
│ │ Layer 3: Skills Hub + Eval + Learnings Loop │ │
│ │ Layer 2: Business Brain + Context Folders │ │
│ │ Layer 1: Agent Router + Standards + Profiles │ │
│ └──────────────────────────────────────────────────────┘ │
└──────────────────────────────────────────────────────────────┘
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.
- 4d ago First seen · 456 lines · 5,932 tokens per session scan A ccabbef350fa
agentic-os AGENTS.md is an instructions file published in the GitHub repository modimihir07/agentic-os (164 stars, last pushed 23d ago), licensed MIT. It adds 5,932 tokens to every session, about $0.0297 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
agentsys AGENTS.md
AGENTS.md instructions for agent-sh/agentsys, covering project memory: agentsys, critical rules (priority order), architecture, commands and core workflow.
AIPass CLAUDE.md
Claude Code instructions for AIOSAI/AIPass, covering aipass, startup protocol and memories.
AIPass AGENTS.md
AGENTS.md instructions for AIOSAI/AIPass, covering aipass, startup protocol and memories.
Hive CLAUDE.md
Instructions for chiruu12/Hive, covering hive development, project overview, architecture, tech stack and code conventions.
gawkbot CLAUDE.md
Claude Code instructions for najmuzzaman-mohammad/gawkbot, a project described as: Gawkbots are your AI teammates who collaborate over shared context. Supports Claude Code, Codex, OpenClaw, OpenCode, local LLMs.
rustyhand AGENTS.md
AGENTS.md instructions for ginkida/rustyhand, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.