perceiving-objects-oneshot

perceiving-objects-oneshot is a skill for Claude Code, Codex from graph-robots/open-robot-skills. It costs 149 tokens per session (1,539 once invoked), scanned A, original, Apache-2.0.

A lightweight one-pass skill for finding and outlining a 3D object in an image. It detects possible objects, asks a vision model to choose one, segments it, and calculates its 3D position and bounding shape.

In plain words
What is it for?
Use it for generic, visible objects in clear scenes, especially when processing items one at a time; use another approach for small or cluttered targets.
Why use it?
It provides a clean not-found result when no object matches, making it suitable for loops that stop when nothing remains to process.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Part of the open-robot-skills plugin — 15 skills shipped together

Good fit Use it for generic, visible objects in clear scenes, especially when processing items one at a time; use another approach for small or cluttered targets.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/graph-robots/open-robot-skills/perceiving-objects-oneshot
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.

Any agent
npx skills add graph-robots/open-robot-skills --skill perceiving-objects-oneshot
Clone the repo
git clone --depth 1 https://github.com/graph-robots/open-robot-skills

Made for: Claude Code, Codex.

Or install open-robot-skills, the plugin that ships this one along with the rest of its 15 skills.

Wrote 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.

agentmods badge for perceiving-objects-oneshot

README.md
[![agentmods](https://agentmods.dev/badge/skills/graph-robots/open-robot-skills/perceiving-objects-oneshot.svg)](https://agentmods.dev/skills/graph-robots/open-robot-skills/perceiving-objects-oneshot)
Your own site
<a href="https://agentmods.dev/skills/graph-robots/open-robot-skills/perceiving-objects-oneshot"><img src="https://agentmods.dev/badge/skills/graph-robots/open-robot-skills/perceiving-objects-oneshot.svg" alt="Measured on agentmods" height="20"></a>
Per session 149 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,539 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00149 $0.01539
Opus 5 $0.00075 $0.00770
Sonnet 5 $0.00030 $0.00308
Haiku 4.5 $0.00015 $0.00154

Measured 8d ago against content hash 1862a6bb19d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

perceiving-objects-oneshot 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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/perceive_simple.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/perceiving-objects-oneshot/SKILL.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

perceiving-objects-oneshot

Single VLM call over a set-of-marks overlay. Pipeline:

observe → perceive → filter_obb

perceive runs:

  1. grounding-dino.detect with a broad object. text prompt
  2. One vlm.query showing the image with letter-labeled boxes: "Which letter is the ? Reply with one letter or 'none'."
  3. On none: emit found: False so the subgraph exits not_found. On a letter: sam3.segment_box on the chosen box, geometry.mask_to_world_points for the cloud.

When to use

  • Clean-all-items / multi-item loops where the cycle needs a clean "no match" signal to terminate via target.not_found → done.
  • Tasks where the target description is generic ("any item on the floor", "the next remaining grocery item") rather than a specific scene-spec id.
  • Uncluttered scenes with distinct, reasonably sized targets where the set-of-marks letter pick is reliable.

When NOT to use

  • Small / cluttered targets (< 40 px wide) — prefer perceiving-objects whose pairwise crop tournament is far more reliable in that regime.

3 states: observe → perceive → filter_obb (mirrors perceiving-objects).

State details:

About object_name below: it is a literal Python string — the natural noun phrase for the object you are perceiving, drawn from this subgraph's description (e.g. "alphabet soup", "basket", "any grocery item on the floor"). It is a constant per subgraph instance, NOT a binding. DO NOT write Ref("in.object_name") or any other Ref(...); the coordinator does not declare object_name as a subgraph input. Write the string directly, e.g. "object_name": "any grocery item on the floor". The same rule applies to object_description if you set it.

  1. observetype: tool, tool: "robot.get_observation", inputs: {}. Connector tool; flat name only.
  2. perceivetype: script, file scripts/<sg>/perceive_simple.py from this bundle. Inputs: cameras=Ref("observe.cameras"), object_name="<noun phrase from the subgraph description>", plus any optional literals (object_description, dino_prompt). Returns {found, cloud, mask, score}. When the VLM picks "none" or DINO emits no detections, found is False and the downstream filter_obb step then raises (empty cloud) — caught by the subgraph's on_error: "not_found" exit.
  3. filter_obbtype: tool, tool: "geometry.filter_and_compute_obb", inputs={"points": Ref("perceive.cloud")}. Returns {"obb": <OrientedBoundingBox>}.

Read the full file on GitHub · 150 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.

  1. 8d ago First seen · 150 lines · 149 tokens per session scan A 1862a6bb19d7

Subscribe to this mod's changes

perceiving-objects-oneshot is a skill published in the GitHub repository graph-robots/open-robot-skills (39 stars, last pushed yesterday), licensed Apache-2.0. It adds 149 tokens to every session and 1,539 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

mjlab-to-mjswan

Port an mjlab task to mjswan: turn a local or remote GitHub repo that registers mjlab tasks into a browser app. Use when the user wants to run, visualize, or deploy an mjlab task (theirs or a third party's) in the browser with mjswan.

ttktjmt/mjswan · 0 tokens

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…

graph-robots/graph-as-policy · 195 tokens

habitat-gs-train

Train and evaluate a navigation policy in the habitat-gs simulator. Covers the full generate-episodes → train → evaluate flow for PointNav / ImageNav / ObjectNav (Habitat-Lab + DDPPO reinforcement learning) and for Vision-and-Language Navigation (StreamVLN, Uni-NaVid). Use when the user wants to train, fine-tune…

zju3dv/habitat-gs · 114 tokens

authoring-pipelines

Use when the user wants a bagel data pipeline — reducing a log to windows around events ("keep 30s around every hard brake"), recurring snippets/GIFs/exports, or any tasks-and-gates automation over robot data.

Extelligence-ai/bagel · 52 tokens

agent-platform-rag-engine-management

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…

google/skills · 85 tokens

agent-platform-model-registry

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

google/skills · 60 tokens