A system called GaP, short for graph-as-policy, that turns natural-language robot tasks into typed skill graphs. The graphs call tools or scripts and use checkpoints to verify progress in a simulator or on supported robots.

Use it to build and run robot skills, connect perception and planning tools, manage skill registries, and execute tasks in simulation or, with explicit approval, on real robots.

It makes robot task execution explicit and checkable instead of relying on an unstructured sequence of actions.

gap — Skill by graph-robots

Install

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.

agentmods

npx agentmods add skills/graph-robots/graph-as-policy/gap

Any agent

npx skills add graph-robots/graph-as-policy --skill gap

Clone the repo

git clone --depth 1 https://github.com/graph-robots/graph-as-policy

Made for: Claude Code, Codex.

Or install agent, the plugin that ships this one along with the rest of its 1 skill.

Per session 195 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,386 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00195	$0.03386
Opus 5	$0.00097	$0.01693
Sonnet 5	$0.00039	$0.00677
Haiku 4.5	$0.00019	$0.00339

Measured 3d ago against content hash e3b8c1a321f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gap 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.

agent/skills/gap/SKILL.md · 287 lines

How it starts

The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.

graph-as-policy — GaP

GaP compiles robot tasks into typed, verified skill graphs and executes them. The policy is the graph: nodes call tools (perception models, planners, robot motions) or run skill scripts; postcondition checkpoints verify progress against the simulator state. Two kinds of repos exist:

the engine (graph-as-policy, imports as gap) — CLI, runtime, builder, codegen, connectors (LIBERO sim / real Franka & UR);
skill registries — directories of bundles (skills/<name>/SKILL.md strategies, tools/<name>/SKILL.md model-backed tools). open-robot-skills is the canonical public registry, normally cloned side-by-side with the engine and auto-discovered. Any number of registries layer by precedence.

Ground truth: gap <command> --help is authoritative; references/cli.md here is a generated snapshot. When working inside a checkout, prefer its docs/ (design.md, runtime.md, skills.md, safety.md) over the digests in this skill.

SAFETY — standing rules

NEVER run gap run --real ... or gap.connector.real(...) unless the human has explicitly confirmed that specific run in this conversation. Real-robot work requires a human with the E-stop in hand and docs/safety.md read. Do not weaken this gate, ever.
Sim-first, always: validate (gap run <graph> --validate-only), then sim (--sim), and only then discuss real hardware.
Use --checkpoints raise on anything real; warn (the default) in sim.
Never claim a task succeeded without evidence: checkpoint pass in the trace, sim.check_success, or gap benchmark --gate.
Never commit API keys or tokens; set them as env vars.

0. Bootstrap / install check

Always start by finding out what exists and what can run:

uv run gap check            # inside a checkout (or just `gap check` if on PATH)
gap check --format json     # machine-readable; parse this when deciding

If the CLI is missing, set up from scratch (Linux; GPU needed for sim):

Read the full file on GitHub · 287 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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 · 287 lines · 195 tokens per session scan A e3b8c1a321f1

Subscribe to this mod's changes

gap is a skill published in the GitHub repository graph-robots/graph-as-policy (124 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 195 tokens to every session and 3,386 once invoked, about $0.0010 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.

Hardware and IoT LLM agents manipulation robotics

bambu-labs

Dry-run, upload, and cautiously initiate local Bambu Lab print jobs from validated plain .gcode, using Bambu LAN FTPS/MQTT handoffs.

earthtojake/text-to-cad · 38 tokens

sdf

SDFormat/SDF model and world authoring, validation, and simulator handoff. Use for .sdf files, SDFormat XML, models, worlds, links, joints, poses, frames, inertials, visual/collision geometry, mesh URIs, sensors, lights, physics, plugins, includes, Gazebo, static SDF review, or simulator-specific metadata. Do not use…

earthtojake/text-to-cad · 88 tokens

srdf

MoveIt2 SRDF authoring, validation, and planning-semantics workflow. Use when creating, editing, inspecting, or validating .srdf files, MoveIt planning groups, virtual joints, passive joints, end effectors, group states, disabled collisions, URDF-paired planning semantics, or SRDF handoff for live review. Use the URDF…

earthtojake/text-to-cad · 110 tokens

gcode

Generate, inspect, dry-run, and statically validate plain FDM .gcode from 3D mesh files by orchestrating real slicer CLIs. Use when Codex needs to slice .stl, .obj, unsliced .3mf, .ply, .glb, or .gltf into printer-profiled G-code, discover local slicer backends, inspect whether a mesh is slice-ready, or validate…

earthtojake/text-to-cad · 102 tokens

step-parts

Find, evaluate, and download common purchasable CAD parts from step.parts, including named off-the-shelf actuators, servos, motors, electronics boards, connectors, screws, bolts, nuts, washers, bearings, standoffs, and other catalog components. Use when Codex needs to search the hosted step.parts catalog before…

earthtojake/text-to-cad · 119 tokens

urdf

URDF robot description authoring and validation. Use when creating, editing, inspecting, validating, or debugging .urdf files, robot links, joints, limits, inertials, visual/collision geometry, mesh references, frame conventions, or robot-description artifacts. Use the SRDF skill for MoveIt2 semantic groups and…

earthtojake/text-to-cad · 106 tokens