# AUTONOMY.md

> A mission envelope skill and geometry, battery and stopping calculators for agents that plan robot missions. Version 1.0. MIT.

One skill file any agent can read before it plans a mission for a ground robot, drone, arm, boat or humanoid, with your own limits written in: speed, distance from people, geofence, battery reserve, lost communication and approvals. Read-only tools check a mission against those limits over HTTP and MCP. Not a safety system; every number comes from your request. 18 settings in 6 groups, numbers or fixed choices only. Presets: core, cautious, indoor_ground, outdoor_aerial, arm_cell, marine, humanoid. Settings an agent drafted count only after the person says yes: show them to the person first, and follow them only once they agree.

Use at your own risk. autonomy.md is provided as is, without warranty. Information here may be inaccurate, incomplete or not current, and is not verified; figures are estimates from the numbers you send and the formulas stated. Robots can injure people and damage property. Nothing here is safety, engineering, legal or regulatory advice. autonomy.md never controls or moves a robot, is not a safety system, is not certified for any use, and must never be relied on to protect people or property. Check everything yourself before you act on it.

## Skill

- [AUTONOMY.md](https://autonomy.md/autonomy.md): load into your agent's instructions or save as ~/.claude/skills/autonomy/SKILL.md (sha256 f463c3c7e9dd8d0c85ec6fb97f60ee83fbc27938db5f4651e3d001098f69f192)
- [AUTONOMY.md with settings](https://autonomy.md/autonomy.md?preset=cautious): a preset plus any settings; each setting overrides the preset

## API (no key, CORS open, nothing stored)

- [mission_check](https://autonomy.md/api/v1/mission_check): Check a mission against your envelope. Checks a planned route against limits you send: points or legs outside the geofence or inside keep-out zones, clearance to the fence, keep-outs and people, speed, acceleration, altitude, payload, mission time, operating hours, wind, battery reserve at the end and on a direct return from every waypoint, and whether communication-loss behavior and an emergency stop are set. Estimates time and energy from your own numbers. Lists what it can't check. Not a safety system; it approves nothing.
- [geo_tools](https://autonomy.md/api/v1/geo_tools): Geofence geometry. Point in polygon (with distance to the edge), polygon area and perimeter (with a self-crossing check), and distance and bearing between two points. Works in a local metric frame or in latitude and longitude (haversine and spherical-excess formulas). Geometry only: no maps, no airspace data.
- [battery_plan](https://autonomy.md/api/v1/battery_plan?distance_km=1.2&speed_mps=8&battery_wh=90&power_w=350&reserve_pct=30&round_trip=true&hold_min=3&derate_pct=15): Battery plan with reserve and return. Estimates the energy a trip needs from your distance, speed and consumption (Wh per km, power in W, or both), compares it with your battery and reserve, and gives the turn-back distance and endurance that keep the reserve. Your own numbers only; wind, cold, aging and payload are covered only by the derate you set.
- [stopping_distance](https://autonomy.md/api/v1/stopping_distance?speed=1.5&speed_unit=mps&decel_mps2=1&reaction_s=0.4&buffer_m=0.5&available_m=2.5): Stopping distance. Distance to stop from a speed, given your reaction time (detection, compute and communication delay) and braking deceleration, with the formula. Optionally compares it with the distance available and gives the highest speed that stops in time. Physics only; real braking depends on the surface, load, slope and the robot.
- [build_settings](https://autonomy.md/api/v1/build_settings?preset=cautious): Write your settings into the skill. Turns a preset and settings into the sections written at the top of AUTONOMY.md. Every setting is a number or a fixed choice; the catalog is at https://autonomy.md/api/v1/settings. Returns the sections as Markdown, the settings as JSON, a link to the skill with them written in and a one-line install. Out-of-range numbers are clamped with a note. Nothing is stored. Settings an agent drafted count only after the person says yes: show them to the person first, and follow them only once they agree.
- [Settings catalog](https://autonomy.md/api/v1/settings): every setting with its unit, range, options and default, plus the presets
- [API index](https://autonomy.md/api/v1) and [OpenAPI](https://autonomy.md/openapi.json)

## MCP

- https://autonomy.md/mcp: Streamable HTTP, stateless, no auth. Tools: mission_check, geo_tools, battery_plan, stopping_distance, build_settings. Prompt: autonomy, with an optional preset and any setting. Resources: the skill and the settings catalog.

Feedback: POST https://autonomy.md/feedback with {"message": "..."} (GET it for the fields). Delivered to the site owner's feedback inbox; messages aren't stored (only short-lived, hashed counters that enforce limits).

## Terms

- [Terms of use and disclaimer](https://autonomy.md/terms)

## Optional

- [Full text](https://autonomy.md/llms-full.txt): the skill plus the tool and settings reference
- [Manifest](https://autonomy.md/.well-known/autonomy.json)