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 agents/pome223/missionos/contractsgit 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/agents/pome223/missionos/contracts)<a href="https://agentmods.dev/agents/pome223/missionos/contracts"><img src="https://agentmods.dev/badge/agents/pome223/missionos/contracts.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 | $0.00000 | $0.02513 |
| Opus 5 | $0.00000 | $0.01256 |
| Sonnet 5 | $0.00000 | $0.00503 |
| Haiku 4.5 | $0.00000 | $0.00251 |
Grade A, and why
contracts 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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MissionOS Contracts
MissionOS code should preserve these boundaries.
CLI
The CLI is an operator surface. It may:
- submit operator instructions to the Gateway
- record approval or rejection intent through Gateway routes
- display task status, timeline events, runtime snapshots, and map artifacts
- send explicit operator-approved recovery commands
The CLI must not:
- turn an AI proposal into dispatch authority
- infer delivery completion from ACK alone
- hide missing runtime evidence behind successful command output
Gateway
The Gateway is the network boundary. It may expose routes for:
- conversation and planning
- operator approval
- execution request creation
- task lookup and timeline lookup
- recovery dispatch
- map and status surfaces
The Gateway must preserve task records and timeline events as auditable evidence. It should fail closed when required approval, dispatch, or runtime evidence is missing.
Core
Core packages own shared schemas and claim semantics. They should not import CLI, Gateway server internals, simulator runtimes, or hardware adapters.
SITL And Runtime Adapters
Runtime adapters are opt-in execution boundaries. They may produce runtime evidence, but they must not rewrite prior proposal or approval facts.
Hardware Adapter Contract
The Real Hardware Bridge v1 starts with hardware-adapter evidence contracts in
src/runtime/hardware_adapter_contract.py, a projection from the existing PX4
bench arm/disarm executor, and a bounded ROS2/Nav2 ground-robot adapter wrapper
and Unitree SDK2/MuJoCo adapter wrapper around injected client boundaries. It is
not a field robot, drone, MAVSDK, or outdoor integration.
HardwareAdapter is a structural protocol for future adapters. The current
runtime implementation is the existing PX4 props-removed bench executor plus
adapter artifacts plus Nav2 and Unitree client-wrapper slices, not a standalone
fake adapter route.
Hardware adapters must separate:
- capability declaration
- preflight
- dispatch candidate
- operator approval
- dispatch request
- ACK
- progress observation
- completion claim
- completion scope
- physical execution
- safe stop or abort
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 · 244 lines · 0 tokens per session scan A 32234445cc81
contracts is an agent published in the GitHub repository pome223/missionos (2 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,513 tokens. 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 agents, from other repositories
Anti-Vibe Writing Dev
Use when developing anti-vibe-writing, a writing skill for AI agents that rewrites generated drafts into a more classic, polished, human style. Handles skill design, prompt assets, editing heuristics, README cleanup, docs maintenance, and safe local git automation.
codebase-analyzer
Analyzes codebase implementation details. Call the codebase-analyzer agent when you need to find detailed information about specific components. As always, the more detailed your request prompt, the better! :).
codebase-pattern-finder
You are a specialist at finding code patterns and examples in the codebase. Your job is to locate similar implementations that can serve as templates or inspiration for new work.
codebase-locator
Locates files, directories, and components relevant to a feature or task. Call codebase-locator with human language prompt describing what you're looking for. Basically a "Super Grep/Glob/LS tool" — Use it if you find yourself desiring to use one of these tools more than once.
thoughts-analyzer
The research equivalent of codebase-analyzer. Use this subagenttype when wanting to deep dive on a research topic. Not commonly needed otherwise.
thoughts-locator
Discovers relevant documents in thoughts/ directory (We use this for all sorts of metadata storage!). This is really only relevant/needed when you're in a reseaching mood and need to figure out if we have random thoughts written down that are relevant to your current research task. Based on the name, I imagine you can…