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 TidyBot-Services/Tidybot-Universe --skill tidybot-skill-devgit clone --depth 1 https://github.com/TidyBot-Services/Tidybot-UniverseWrote 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/tidybot-services/tidybot-universe/tidybot-skill-dev)<a href="https://agentmods.dev/skills/tidybot-services/tidybot-universe/tidybot-skill-dev"><img src="https://agentmods.dev/badge/skills/tidybot-services/tidybot-universe/tidybot-skill-dev/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/tidybot-services/tidybot-universe/tidybot-skill-dev"><img src="https://agentmods.dev/badge/skills/tidybot-services/tidybot-universe/tidybot-skill-dev.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00100 | $0.00759 |
| Opus 5 | $0.00050 | $0.00380 |
| Sonnet 5 | $0.00020 | $0.00152 |
| Haiku 4.5 | $0.00010 | $0.00076 |
Grade A, and why
tidybot-skill-dev 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tidybot Skill Development
Before You Start
- Read the SDK guide first:
GET http://<ROBOT_IP>:8080/docs/guide/html— do not guess or improvise. Seerobot-sdk-refskill. - Check existing skills: Fetch
https://raw.githubusercontent.com/tidybot-skills/wishlist/main/catalog.json. Use or extend what exists. Local skills usetb-prefix. - Chain if possible. Use
tidybot-bundle <skill-name>to combine skills. Estimate success = product of individual rates. Chaining tested skills is always preferable to untested new code. - Build new only as last resort. Research first (internet, papers), then check services (see
active-servicesskill).
Naming Convention
- Robot skills use the
tb-prefix:tb-pick-up-object,tb-center-object - In-development skills use the
dev-tb-prefix:dev-tb-my-skill - Management/reference skills use the
tidybot-prefix (you won't create these)
All new robot skills must start with tb- (or dev-tb- while in development).
Skill Structure (OpenClaw format)
dev-tb-my-skill/ # dev-tb- prefix while developing
├── SKILL.md # Frontmatter (name, description) + instructions
└── scripts/
├── main.py # Skill code (submitted to robot)
└── deps.txt # Dependencies (one tb-skill-name per line)
Developing
- Connect to the robot API using SDK guide patterns. Test sensor reads first.
- Prototype iteratively — use SDK methods (not invented ones), test on hardware, use rewind on failure.
- Save with
dev-tb-prefix (e.g.dev-tb-my-skill/) and OpenClaw skill structure.
Testing & Trials
- Run the skill multiple times in varied conditions.
- Record success/failure per trial. Any code change resets stats — re-test from scratch.
- Debug with
print()+ poll/code/status?stdout_offset=N&stderr_offset=N. Prefer recorded frames over live camera. - Max 10 trials/day per skill during heartbeat practice.
- Use rewind freely — it's your safety net.
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 · 59 lines · 100 tokens per session scan A 836197b7aba4
tidybot-skill-dev is a skill published in the GitHub repository TidyBot-Services/Tidybot-Universe (56 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 100 tokens to every session and 759 once invoked, about $0.0005 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
jetson-video-pipeline
Use when executing and verifying Jetson Video Codec SDK or PyNvVideoCodec encode/decode, transcode, segmentation, container decode, AV1, or acceptance workflows with exact artifact handoffs.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
holohub-app-lifecycle
Use for non-failing HoloHub app work with ./holohub: scaffold, build, run, test, visual evidence, lint, and flow benchmarking.
code-plan
Turn a task description and repository into a structured implementation plan (files to create, files to modify, tests to add, risks).
ros2-robotics
Best practices for ROS 2 robotics development, covering package structure, nodes, topics/services/actions, launch files, QoS, tf2 transforms, and testing. Use when creating ROS 2 packages, writing nodes in rclpy or rclcpp, defining custom messages/services/actions, writing launch files, configuring QoS profiles…
SmartHome Video Anomaly Benchmark
VLM evaluation suite for video anomaly detection in smart home camera footage.