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 skills add graph-robots/open-robot-skills --skill perceiving-next-itemgit clone --depth 1 https://github.com/graph-robots/open-robot-skillsWrote 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/open-robot-skills/perceiving-next-item)<a href="https://agentmods.dev/skills/graph-robots/open-robot-skills/perceiving-next-item"><img src="https://agentmods.dev/badge/skills/graph-robots/open-robot-skills/perceiving-next-item/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/skills/graph-robots/open-robot-skills/perceiving-next-item"><img src="https://agentmods.dev/badge/skills/graph-robots/open-robot-skills/perceiving-next-item.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00209 | $0.03356 |
| Opus 5 | $0.00105 | $0.01678 |
| Sonnet 5 | $0.00042 | $0.00671 |
| Haiku 4.5 | $0.00021 | $0.00336 |
Grade A, and why
perceiving-next-item 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 10d 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 — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
perceiving-next-item
The repeating head of a pack-all loop. One robot.get_observation feeds two
perceptions — the destination container and the next remaining item —
and a decide router turns the item verdict into the loop's continue/terminate
signal. It is perceiving-objects (the reliable pairwise-tournament perception)
composed with (a) a second perception for the container and (b) a clean none
exit, so a "pick up every object and place it in the basket" workflow has one
subgraph that answers "is there still an item, and where is the basket?" every
pass.
Detection uses the same pairwise VLM crop tournament as perceiving-objects
(~30% → 97% object-ID over a one-shot Set-of-Marks pick on the LIBERO-PosVar
study). The clean loop terminator comes from the item's container-excluding
object_description: once only the basket remains, the tournament + verify
gate answer "no grocery item", perceive_item returns found=False, and the
decide router emits none → the loop exits to done.
When to use
- The repeating head of a pack-all / clean-all-items loop (
transportroutes its success edge back here), where each pass must reliably decide "grasp the next item" vs "everything is packed, stop". - When the downstream place needs a fresh container OBB every pass (this
skill emits
container_obb/container_mask/container_cloudalongside the target).
When NOT to use
- Single pick-and-place (grab ONE named object). Use
perceiving-objects(one target, no loop, no container co-perception). - You want the container localized once, out of the loop. If the container
never moves and you prefer to perceive it a single time before the loop, use a
plain
perceiving-objectssubgraph for the basket +perceiving-objects-oneshotfor the looping target. This skill deliberately re-localizes both each pass (robust to a nudged basket, one observation, one cleannone). - Cluttered scenes with look-alike distractors. Prefer
perceiving-objectsfor the target identity — its pairwise-tournament plusobject_descriptionhints disambiguate look-alikes (it lacks the clean loopnone, so you would add your owndecide).
What ships with it
7 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.
- examples/canonical_subgraph.json 2.4 KB
- prompts/vlm_pairwise.md 718 B
- references/geometry_calling_conventions.md 1.7 KB
- references/perception_pipeline_invariants.md 1.2 KB
- scripts/decide_next_item.py 9.3 KB runs code
- scripts/exterior_view.py 771 B runs code
- scripts/perceive_dino_vlm.py 36 KB runs code
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.
- 10d ago First seen · 253 lines · 209 tokens per session scan A 51b3e7f045f1
perceiving-next-item is a skill published in the GitHub repository graph-robots/open-robot-skills (41 stars, last pushed yesterday), licensed Apache-2.0. It adds 209 tokens to every session and 3,356 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.
Other skills, from other repositories
gap
Program robots with GaP (graph-as-policy) — compile natural-language tasks into typed, verified robot skill graphs and run them on simulators or real robots. Use when the user mentions GaP or graph-as-policy, robot manipulation, robot skills, robot tools or capabilities, skill registries, open-robot-skills, LIBERO or…
bambu-labs
Dry-run, upload, and cautiously initiate local Bambu Lab print jobs from validated plain .gcode, using Bambu LAN FTPS/MQTT handoffs.
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…
cad-viewer
Start CAD Viewer and return review links for CAD and robot-description files. Use when visually reviewing .step, .stp, .glb, .stl, .3mf, .dxf, .urdf, .srdf, or .sdf files, especially when handed off from CAD, URDF, SRDF, or SDF generation skills.
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…
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…