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 skills/graph-robots/graph-as-policy/fixture-skillnpx skills add graph-robots/graph-as-policy --skill fixture-skillgit 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/skills/graph-robots/graph-as-policy/fixture-skill)<a href="https://agentmods.dev/skills/graph-robots/graph-as-policy/fixture-skill"><img src="https://agentmods.dev/badge/skills/graph-robots/graph-as-policy/fixture-skill.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 | $0.00036 | $0.00208 |
| Opus 5 | $0.00018 | $0.00104 |
| Sonnet 5 | $0.00007 | $0.00042 |
| Haiku 4.5 | $0.00004 | $0.00021 |
Grade A, and why
fixture-skill 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.
What it actually says
fixture-skill
A minimal skill bundle: one canonical script, one prompt template. Exists only for the loader test suite.
When to use
- Never, outside of tests.
What ships with it
2 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.
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 · 32 lines · 36 tokens per session scan A 180441a28630
fixture-skill 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 36 tokens to every session and 208 once invoked, about $0.0002 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.
Other skills, from other repositories
transporting-objects
Move the currently-held object to a destination and release. The gripper enters this subgraph holding the object; on exit the object has been placed. For a walled container (basket / bin / box / tote) the default is a straight-Z descent to inside the walls (transportdescendlinear → release); for placement ONTO a…
grasping-short-axis
Deterministic short-axis-aligned grasp with CuRobo. The grasp pose is computed geometrically (NOT sampled/scored) — the gripper approaches straight down with its finger-opening axis locked to the OBB's SHORTER horizontal axis, so the jaws close ACROSS the narrow dimension of an elongated target. Use for pan/pot…
perceiving-next-item
Loop-head perception for pack-all / clean-all-items tasks. From ONE observation it localizes BOTH the destination container (basket, bin, box) AND the next remaining target item, using the pairwise VLM crop tournament with a container-excluding description so the target is never confused with the basket, then makes a…
grasping-with-planner
Top-down grasping via a fast axis-locked linear descend with a collision-aware cuRobo fallback. A single graspdescendlinear node rises, translates over the target, and descends straight down (Z-locked, orientation held) onto the object; if the straight-line solve is infeasible (far-edge reach, no IK for the fixed…
perceiving-objects
Fast single-path 3D object perception. Runs Grounding-DINO broad detection, a pairwise VLM crop tournament to identify the target box, SAM3 box segmentation, and depth back-projection to a world-frame point cloud, finished by geometry.filterandcomputeobb for a clean oriented bounding box, mask, and cloud. Multi-camera…
perceiving-object-parts
Hierarchical perception for subpart targeting. Detects a parent object first (DINO+VLM), crops the camera image to the parent's bounding box, then detects and segments the named subpart inside the crop (DINO + SAM3), and uncrops + fuses depth to a world-frame OBB/mask/cloud — plus the parent object's OBB and cloud for…