Claw3D is a self-hosted 3D virtual office where AI agents can collaborate, review code, run standups, execute tasks, and display their work in real time. It is for people running AI teams on their own infrastructure, with support for several agent runtimes. The catalogue skills and instruction support working with this agent workspace.
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 iamlukethedev/Claw3D --skill todo-boardgit clone --depth 1 https://github.com/iamlukethedev/Claw3DWrote 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/iamlukethedev/claw3d/todo-board)<a href="https://agentmods.dev/skills/iamlukethedev/claw3d/todo-board"><img src="https://agentmods.dev/badge/skills/iamlukethedev/claw3d/todo-board/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/iamlukethedev/claw3d/todo-board"><img src="https://agentmods.dev/badge/skills/iamlukethedev/claw3d/todo-board.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 | $0.00012 | $0.00893 |
| Opus 5 | $0.00006 | $0.00447 |
| Sonnet 5 | $0.00002 | $0.00179 |
| Haiku 4.5 | $0.00001 | $0.00089 |
Grade A, and why
todo 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 9d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- todo — 95% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TODO Board
Use this skill when the user wants to manage a shared task list for the current workspace.
Trigger
{
"activation": {
"anyPhrases": [
"todo",
"todo list",
"blocked task",
"blocked tasks",
"add to my todo",
"show my todo"
]
},
"movement": {
"target": "desk",
"skipIfAlreadyThere": true
}
}
When this skill is activated, the agent should return to its assigned desk before handling the request.
- If the user asks from Telegram or any other external surface to add, block, unblock, remove, or read TODO items, treat that as a trigger for this skill.
- The physical behavior for this skill is: go sit at the assigned desk, then perform the TODO board workflow.
- If the agent is already at the desk, continue without adding extra movement narration.
Storage location
The authoritative task file is todo-skill/todo-list.json in the workspace root.
- Always treat that file as the source of truth.
- Never rely on chat memory alone for the latest task state.
- Create the
todo-skilldirectory andtodo-list.jsonfile if they do not exist.
Required workflow
- Read
todo-skill/todo-list.jsonbefore answering any task-management request. - If the file does not exist, create it with the schema in this document before continuing.
- After every add, remove, block, or unblock action, write the full updated JSON back to disk.
- If the file exists but is invalid JSON or does not match the schema, repair it into a valid structure, preserve any recoverable items, and mention that repair in your response.
- If the user request is ambiguous, ask a clarifying question instead of guessing.
Supported actions
- Add a task. Create a new item unless an equivalent active item already exists.
- Block a task.
Change the matching item to
status: "blocked". If the task does not exist and the request is clear, create it directly as blocked. - Unblock a task.
Change the matching item back to
status: "todo"and clearblockReason. - Remove a task. Delete only the matching item. If multiple items could match, ask for clarification.
- Read the list.
Summarize tasks grouped into
TODOandBLOCKED.
What ships with it
1 file 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.
- 9d ago First seen · 110 lines · 12 tokens per session scan A 0d1ffe9dc88e
todo is a skill published in the GitHub repository iamlukethedev/Claw3D (2,206 stars, last pushed 19d ago), licensed MIT. It adds 12 tokens to every session and 893 once invoked, about $0.0001 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
task-manager
Capture actionable user requests as persistent tasks, update task status as work progresses, and keep a shared task store in sync. Use when a user asks an agent to do work, check progress, block a task, complete a task, or manage the Kanban board.
todo
Maintain a shared workspace TODO list with blocked tasks.
soundhermes
Control Spotify playback, search music, and return shareable music links.
intelligence-docs
Keeps the CopilotKit Intelligence landing page in sync when a new Intelligence feature ships or when Intelligence docs are added, renamed, or removed. Use when adding Intelligence capabilities, writing or moving pages under docs/intelligence, editing IntelligenceFeatureCards, or changing…
record-gotchas
Capture surprises, workarounds, and rough edges hit while consuming the public surface of Prisma Next, Prisma Compute, or Prisma Postgres — anything a real user of these products would experience. Fires whenever an operator (or agent) writes a workaround, hits a surprising failure mode, or finds undocumented behaviour…
commonly
You are a member of a Commonly workspace — a shared space where humans and AI agents from any origin collaborate in pods (chat rooms with memory). Use this whenever you are connected to Commonly via the commonly MCP tools: to read what's happening, post, remember things across sessions, react, DM other agents, and…