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/robium-ai/robium/datanpx skills add robium-ai/robium --skill datagit clone --depth 1 https://github.com/robium-ai/robiumWhat 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 | $0.00153 | $0.02869 |
| Opus 5 | $0.00077 | $0.01435 |
| Sonnet 5 | $0.00031 | $0.00574 |
| Haiku 4.5 | $0.00015 | $0.00287 |
Grade A, and why
data 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 2d 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.
This is a copy
95% identical to data — 50 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
data
The data-sourcing umbrella for robium. Before any policy gets trained, something
has to decide where the training data comes from (an existing hub dataset, data
generated in simulation, or demonstrations collected via teleop on a real robot)
and how it will be stored and versioned once it exists. This skill owns that
selection and the cross-cutting sourcing rules; it does not own hub mechanics
(huggingface), the LeRobotDataset format (lerobot), or the mechanics of
generating synthetic data inside a simulator (isaac-sim, gazebo). It also
does not own training itself; that is lerobot and isaac-lab's territory.
When to use this skill
- Starting any robot-learning task and the data source isn't decided yet; this
is a required early step for the manipulation vertical, the same way
environmentsis a required early step for reproducibility. - The trigger phrases in the description: 'where do we get data', 'training data for the robot', 'dataset for manipulation', 'generate data in sim', 'collect demonstrations'.
- Planning storage format, episode structure, or dataset versioning before a collection or generation effort starts, not after.
- Cross-references: go to the sibling skill instead when the question is:
- Actually pulling, pushing, or browsing a dataset on the Hub →
huggingface. This skill decides which dataset or source strategy to use; it does not own hub auth or transfer mechanics. - The LeRobotDataset directory/Parquet+MP4 shape, recording CLI, or dataset
editing tools →
lerobot. This skill decides whether to record real demonstrations at all;lerobotowns how a recording actually happens. - The mechanics of generating synthetic data inside a simulator (Replicator,
domain randomization, writers) →
isaac-simorgazebo. This skill decides whether sim-generated data is the right call for a task. - Training a policy on the data once sourced →
lerobot(orisaac-labfor the NVIDIA RL stack). - The whole-stack decision this feeds into →
architect(routes here). - Sourcing test data (worlds, models, sample datasets, fixtures, and
goldens for smoke/regression tests) →
test-assets. This skill owns data that trains policies;test-assetsowns data that tests apps.
- Actually pulling, pushing, or browsing a dataset on the Hub →
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.
- 2d ago First seen · 202 lines · 153 tokens per session scan A 75fe9efc599b
data is a skill published in the GitHub repository robium-ai/robium (9 stars, last pushed 4d ago), licensed MIT. It adds 153 tokens to every session and 2,869 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to data, differing in 50 lines, and is treated as a copy.
Other skills, from other repositories
ros2-microros
Skill "ros2-microros" from Leehyunbin0131/claude-ros2-skills, covering micro-ros instructions (ubuntu 24.04 lts & ros 2 jazzy), 1. architecture, 2. documentation entry points, 3. key concepts & patterns and a. embedded client node setup (rclc in c).
ros2-troubleshooting
Diagnose ROS 2 Jazzy faults that reading the code cannot settle: QoS mismatch, sensor-mount and frame errors (REP 103/105), and odometry calibrated against CAD instead of the floor. Ships four runnable pass/fail checks.
gazebo-mcp
Gazebo / gz-sim worlds, models, poses (mock + live bridge). CLI gazebo-mcp + MCP stdio serve. Use when the user mentions gazebo-mcp, /gazebo-mcp, or related domain work. One-command Grok install from GitHub.
attach-end-effector
Mount an end-effector (parallel-jaw gripper, dexterous hand, suction tool, etc.) on a robot arm by attaching its MJCF to the arm's attachmentsite via MuJoCo's MjSpec API. Use when combining an arm MJCF and an end-effector MJCF into a single combined model. Handles known gotchas the underlying script doesn't: mesh…
urdf-to-mjcf
Use when bringing a URDF robot, hand, or CAD-generated model into MuJoCo MJCF and no hand-tuned upstream MJCF exists.
mjcf-to-urdf
Convert an MJCF (MuJoCo's XML format) to URDF for downstream consumers that don't speak MJCF (RViz, pinocchio, ROS-based motion planning, etc.). The conversion is lossy — constraints, position actuators, contact excludes, and keyframes are all dropped. Use this skill ONLY when a URDF-only consumer needs the kinematic…