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/imran-siddique/agent-os/agents-mdgit clone --depth 1 https://github.com/imran-siddique/agent-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/imran-siddique/agent-os/agents-md)<a href="https://agentmods.dev/instructions/imran-siddique/agent-os/agents-md"><img src="https://agentmods.dev/badge/instructions/imran-siddique/agent-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 | $0.00779 | $0.00779 |
| Opus 5 | $0.00390 | $0.00390 |
| Sonnet 5 | $0.00156 | $0.00156 |
| Haiku 4.5 | $0.00078 | $0.00078 |
Grade A, and why
agent-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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent-OS — Coding Agent Instructions
Project Overview
Agent-OS is a governance-first kernel for AI agents — a Python framework providing policy enforcement, semantic intent classification, identity management, and execution control for autonomous AI agents.
Architecture: 4-layer modular kernel
- Layer 1 (Primitives): Core identity (CMVK), credentials (CaaS), execution memory (EMK)
- Layer 2 (Infrastructure): Inter-agent trust protocol (IATP), agent message bus (AMB), agent trust registry (ATR)
- Layer 3 (Framework): Control plane, observability, nexus orchestration
- Layer 4 (Intelligence): Semantic context awareness (SCAK), mute-agent, MCP kernel server
Build & Test Commands
# Install dependencies (development mode)
pip install -e ".[dev]"
# Run all tests
pytest tests/ modules/*/tests -v --tb=short
# Run tests with coverage
pytest tests/ --cov=src/agent_os --cov-report=html --cov-branch
# Type checking
mypy src/
# Lint
ruff check .
# Format
ruff format .
Code Style
- Formatter/Linter: Ruff (line-length: 100, target: Python 3.9+)
- Rules: E, W, F, I (isort), B (bugbear), C4, UP (pyupgrade)
- Type checker: MyPy strict mode with Pydantic plugin
- Docstrings: Google-style
- Imports: Sorted by isort via Ruff
Key Files
| File | Purpose |
|---|---|
src/agent_os/integrations/base.py |
Core governance — GovernancePolicy, BaseIntegration, PolicyInterceptor, event hooks |
src/agent_os/integrations/profiling.py |
@profile_governance decorator |
src/agent_os/base_agent.py |
Base agent class with audit logging |
src/agent_os/stateless.py |
Stateless agent with optional Redis |
tests/test_integrations.py |
Main governance test suite |
modules/ |
14+ modular kernel components |
Coding Conventions
- All public APIs must have type hints (
mypy --strict) - Use
dataclassor PydanticBaseModelfor data structures - GovernancePolicy fields:
max_tokens_per_request,max_tool_calls_per_request,blocked_patterns,allowed_tools,confidence_threshold - Pattern types:
PatternType.SUBSTRING,PatternType.REGEX,PatternType.GLOB - Event types:
GovernanceEventType.POLICY_CHECK,.POLICY_VIOLATION,.TOOL_CALL_BLOCKED,.CHECKPOINT_CREATED - Tests go in
tests/(unit) ormodules/*/tests/(module-specific)
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 · 81 lines · 779 tokens per session scan A ef8a8cefec9d
agent-os AGENTS.md is an instructions file published in the GitHub repository imran-siddique/agent-os (73 stars, last pushed 6mo ago), licensed MIT. It adds 779 tokens to every session, about $0.0039 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
agent-governance-toolkit copilot-instructions.md
Copilot instructions for microsoft/agent-governance-toolkit, covering copilot instructions for agent-governance-toolkit, architecture, build, test, and lint, python and install (editable, all extras).
pydantic-ai AGENTS.md
AGENTS.md instructions for pydantic/pydantic-ai, covering your primary responsibility is to the project and its users, gathering context on the task, ensuring the task is ready for implementation, philosophy and requirements of all contributions.
open-multi-agent AGENTS.md
AGENTS.md instructions for open-multi-agent/open-multi-agent, covering agents.md, repository map, commands, working rules and validation by change type.
waku-agent CLAUDE.md
Instructions for ShenSeanChen/waku-agent, covering waku-agent — working conventions, architecture map (file ↔ diagram box), rules and commands.
Doberman-Core AGENTS.md
AGENTS.md instructions for DobermanCore/Doberman-Core, covering claude.md — doberman operating manual, 0. on startup (every session), 1. what this repository is, 2. architecture & extension points and 3. prime directives (non-negotiable).
orloj AGENTS.md
Instructions for OrlojHQ/orloj, covering orloj agent instructions, must-follow sync rules and working style.