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 task-managergit 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/task-manager)<a href="https://agentmods.dev/skills/iamlukethedev/claw3d/task-manager"><img src="https://agentmods.dev/badge/skills/iamlukethedev/claw3d/task-manager/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/task-manager"><img src="https://agentmods.dev/badge/skills/iamlukethedev/claw3d/task-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 18 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00056 | $0.01092 |
| Opus 5.5 | $0.00022 | $0.00437 |
| Sonnet 5.5 | $0.00011 | $0.00218 |
| Haiku 4.5 | $0.00006 | $0.00109 |
Grade A, and why
task-manager 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 1mo 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Manager
Use this skill for task capture and task lifecycle updates.
Trigger
{
"activation": {
"anyPhrases": [
"add a task",
"create a task",
"track this task",
"task status",
"mark this done",
"block this task",
"what tasks do we have"
]
},
"movement": {
"target": "desk",
"skipIfAlreadyThere": true
}
}
Also use this skill even when those exact phrases are absent if the latest user message is an actionable work request. If the user asks the agent to do something, that request must become a task before the agent proceeds.
Storage location
The authoritative task file is:
${OPENCLAW_STATE_DIR}/claw3d/task-manager/tasks.jsonwhenOPENCLAW_STATE_DIRis set.~/.openclaw/claw3d/task-manager/tasks.jsonotherwise.
Always treat that file as the shared source of truth for the Kanban board.
Required workflow
- Read the task file before handling an actionable request.
- If the file does not exist, create it with the schema in this document.
- If the latest user message is actionable and no matching active task exists, create one immediately.
- Before starting execution, ensure the task is
todoor move it toin_progress. - If work cannot continue, set the task to
blockedand record a short reason innotes. - When work is finished, set the task to
done. - When work needs user review or confirmation, set the task to
review. - After every mutation, write the full updated JSON back to disk.
Matching rules
- Match first by
externalThreadIdwhen the request comes from a stable thread or conversation. - Otherwise match by a concise normalized title that preserves user intent.
- Avoid creating duplicate active tasks for the same request.
Task fields
Each task must include:
idtitledescriptionstatussourcesourceEventIdassignedAgentIdcreatedAtupdatedAtplaybookJobIdrunIdchannelexternalThreadIdlastActivityAtnotesisArchivedisInferredhistory
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.
- 1mo ago First seen · 143 lines · 56 tokens per session scan A 1f679dae1754
task-manager is a skill published in the GitHub repository iamlukethedev/Claw3D (2,375 stars, last pushed 2mo ago), licensed MIT. It adds 56 tokens to every session and 1,092 once invoked, about $0.0002 per session on Opus 5.5. 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.
record-gotchas
Capture surprises, workarounds, and rough edges hit while consuming the public surface of Prisma 8, 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…
product-direction
Judges feature requests, feature pull requests and your own proposals against a repository's written product direction, gives a cited verdict, and records each new no. Use when triaging, labelling or replying to a feature request or a feature pull request, including as an autonomous triage agent; when asked whether a…
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…