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.
git clone --depth 1 https://github.com/graph-robots/graph-as-policyWrote 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/plugins/graph-robots/graph-as-policy/agent)<a href="https://agentmods.dev/plugins/graph-robots/graph-as-policy/agent"><img src="https://agentmods.dev/badge/plugins/graph-robots/graph-as-policy/agent/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/graph-robots/graph-as-policy/agent"><img src="https://agentmods.dev/badge/plugins/graph-robots/graph-as-policy/agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 1mo 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.
What it actually says
{
"name": "gap",
"displayName": "gap — graph as policy",
"description": "Search robot skill registries, check robot/tool capabilities, and program, run, and debug verified robot task graphs (sim-first, safety-gated real) with the gap engine.",
"author": { "name": "graph-as-policy authors", "url": "https://github.com/graph-robots" },
"homepage": "https://github.com/graph-robots/graph-as-policy",
"repository": "https://github.com/graph-robots/graph-as-policy",
"license": "MIT",
"keywords": ["robotics", "robot-manipulation", "robot-skills", "skill-registry", "LIBERO", "simulation", "task-graphs", "open-robot-skills"]
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 195 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 1mo ago First seen · 11 lines scan A 6239307c3713
gap is a plugin published in the GitHub repository graph-robots/graph-as-policy (164 stars, last pushed 4d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.
Other plugins, from other repositories
text-to-cad
The text-to-cad plugin gives your agent local workflows for generating 3D models as STEP, GLB, STL or 3MF files. It also does design for manufacturing checks, generates engineering drawings, and connects to popular 3D printing, sheet metal and CNC fabrication services.
text-to-cad
The text-to-cad plugin gives your agent local workflows for generating 3D models as STEP, GLB, STL or 3MF files. It also does design for manufacturing checks, generates engineering drawings, and connects to popular 3D printing, sheet metal and CNC fabrication services.
claude-homelab marketplace
Plugin marketplace listing 26 plugins: homelab-core, overseerr-mcp, unraid-mcp, unifi-mcp, gotify-mcp.
open-robot-skills
Robot skill bundles for the gap engine — perception, grasping, transport, tracking, and policy-steering strategies (skills/) plus model-backed tool bundles (tools/: SAM3, Grounding DINO, Gemini-ER, Molmo, generic VLM, CuRobo planning, pure-math geometry). Each bundle is an Agent Skills directory; Python deps install…
decocms-ui
Build UI with the decocms product design system (@decocms/ui).
agent-comms
Cross-harness LLM agent communication mesh — rooms, DMs, and presence.