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/pome223/missionos/agents-mdgit clone --depth 1 https://github.com/pome223/missionosWrote 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/pome223/missionos/agents-md)<a href="https://agentmods.dev/instructions/pome223/missionos/agents-md"><img src="https://agentmods.dev/badge/instructions/pome223/missionos/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 5.1 | $0.00407 | $0.00407 |
| Opus 5 | $0.00204 | $0.00204 |
| Sonnet 5 | $0.00081 | $0.00081 |
| Haiku 4.5 | $0.00041 | $0.00041 |
Grade A, and why
missionos 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 5d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
These instructions apply to automated coding agents working in this repository.
Documentation Layers
Keep documentation in two layers:
docs/concepts/anddocs/examples/are for humans. Prefer short, abstract, readable explanations.docs/agents/is for AI agents and maintainers. Prefer explicit contracts, field semantics, verification requirements, and publication rules.
Do not move implementation details into the human layer unless they are required to understand the concept.
Claim Boundaries
Preserve the MissionOS authority split:
LLM judges.
Human approves.
Rules constrain.
Executor acts.
Verifier checks.
Repair loops.
Do not describe an AI proposal as approval, dispatch, execution, landing, delivery completion, or physical execution. Keep these as separate facts.
Public Safety
This repository is private while it is being prepared for publication. Treat all incoming code as a publication event:
- do not import private task databases, private generated output, credentials, local secrets, or unreviewed evidence artifacts
- do not add local-only paths from another workstation or private checkout
- keep hardware and live simulator execution opt-in
- prefer fixtures for public demos and tests
Pull Request Verification
Before opening or updating a pull request, verify the change with a runtime smoke test that exercises the affected production boundary. Unit tests alone are not sufficient for PR readiness when runtime behavior changes.
Examples:
- CLI changes: run the CLI entrypoint with a minimal real invocation.
- Gateway changes: start the Gateway on a loopback port and call the route with a real HTTP or WebSocket client.
- Simulator adapter changes: run the fixture adapter or opt-in SITL smoke that covers the changed boundary.
- Documentation-only changes: run link or formatting checks when available.
Every PR body should include an E2E / Runtime Verification section with the
exact command, scenario, boundary covered, observed result, and limitations.
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.
- 5d ago First seen · 61 lines · 407 tokens per session scan A fe2c91f58fe9
missionos AGENTS.md is an instructions file published in the GitHub repository pome223/missionos (2 stars, last pushed today), licensed Apache-2.0. It adds 407 tokens to every session, about $0.0020 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
humanlayer CLAUDE.md
Claude Code instructions for humanlayer/humanlayer, covering claude.md, repository overview, project 1: humanlayer sdk & platform, components and core concepts.
security-knowledge-base AGENTS.md
Instructions for dinosn/security-knowledge-base, covering security knowledge base agent contract, purpose and boundary, authority and trust, required startup sequence and agent permissions.
mdxg-redline AGENTS.md
Instructions for oubakiou/mdxg-redline, a project described as: Inline review tool for MDXG markdown — capture highlighted comments and export them as structured JSON for LLM agents.
mdxg-redline CLAUDE.md
Instructions for oubakiou/mdxg-redline, a project described as: Inline review tool for MDXG markdown — capture highlighted comments and export them as structured JSON for LLM agents.
security-knowledge-base CLAUDE.md
Instructions for dinosn/security-knowledge-base, a project described as: Local-first, evidence-led security knowledge base with a model-neutral JSON CLI, immutable sources, and human-reviewed proposals.
security-knowledge-base GEMINI.md
Instructions for dinosn/security-knowledge-base, a project described as: Local-first, evidence-led security knowledge base with a model-neutral JSON CLI, immutable sources, and human-reviewed proposals.