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/rangerrick337/operator-os/agents-mdgit clone --depth 1 https://github.com/rangerrick337/operator-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 | $0.02586 | $0.02586 |
| Opus 5 | $0.01293 | $0.01293 |
| Sonnet 5 | $0.00517 | $0.00517 |
| Haiku 4.5 | $0.00259 | $0.00259 |
Grade A, and why
operator-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 3d 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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
⚠️ CORE FRAMEWORK DOCUMENTATION
This file contains the canonical instructions for the 6-Layer Operator OS. It defines the architecture, operating principles, and file organization for AI agent systems.
You operate within a 6-layer architecture that separates concerns to maximize reliability. LLMs are probabilistic, whereas most business logic is deterministic and requires consistency. This system fixes that mismatch.
The 6-Layer Architecture
Layer 1: SOPs (What to do)
- Written in Markdown, live in
Operator Team OS/1. SOPs/ - Human-readable process documentation
- Define goals, context, inputs, outputs, and edge cases
- Natural language instructions, like you'd give a mid-level employee
Layer 2: Agents (Who to be)
- Specialized personas in
Operator Team OS/2. Agents/ - Define voice, expertise, model preference, and decision-making style
- Activated when specific persona/expertise is needed
Layer 2a: The Activation Pattern (How to "Be" an Agent) To create a switchable persona:
- Define (
Operator Team OS/2. Agents/MyAgent.md): The "Resume" (Voice, Model, Tools). - Trigger (
Operator Team OS/4. Workflows/be-my-agent.md): The "Job Order".- Content: "You are now [Agent Name]. Read
Operator Team OS/2. Agents/MyAgent.mdand adopt persona."
- Content: "You are now [Agent Name]. Read
- Sync: Run
workflow-syncto make the slash command available.
Layer 3: Skills (How to execute)
-
Anthropic-format skills in
Operator Team OS/3. Skills/ -
Each skill has
SKILL.md(instructions + YAML frontmatter) +scripts/(code) -
Progressive disclosure: Read YAML frontmatter first, load full instructions only when needed
-
Scripts are deterministic Python—reliable, testable, fast
Layer 4: Workflows (Sequences)
- Live in
Operator Team OS/4. Workflows/(Canonical Source) - Symlinked to
.agent/workflowsfor Antigravity compatibility (allows/slash commands) - Sequential "fire and forget" instructions for repetitive technical tasks
- If Antigravity is used, supports
// turbomode for auto-execution
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.
- 3d ago First seen · 215 lines · 2,586 tokens per session scan A fd1284d4da5e
operator-os AGENTS.md is an instructions file published in the GitHub repository rangerrick337/operator-os (10 stars, last pushed 6mo ago), licensed MIT. It adds 2,586 tokens to every session, about $0.0129 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
openai-agents-python AGENTS.md
AGENTS.md instructions for openai/openai-agents-python, covering contributor guide, policies & mandatory rules, mandatory skill usage, work status reporting and git worktree and branch safety.
codedb AGENTS.md
AGENTS.md instructions for justrach/codedb, covering codedb agent guidelines, what codedb is (and isn't), review guidelines, pre-merge verification and security-sensitive areas.
codedb copilot-instructions.md
Copilot instructions for justrach/codedb, covering codedb — agent instructions, project, rules, filing issues and test style.
Puppetmaster AGENTS.md
Instructions for professorpalmer/Puppetmaster, covering agents.md, first: are you a puppetmaster worker?, default subagent runtime: puppetmaster, when to start a puppetmaster swarm (do this by default) and match the verb to the task shape (single feature ≠ swarm).
claude-code-blueprint CLAUDE.md
Instructions for faizkhairi/claude-code-blueprint, covering global claude behavior rules, verify-after-complete (mandatory), what to verify depends on what was built, verification mindset and after verification.
awesome-reviewers CLAUDE.md
Instructions for baz-scm/awesome-reviewers, covering awesome reviewers — repository guidelines, what this project is, source of truth, site layer and machine interface.