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 zhixuli0406/DuDuClaw --skill duduclaw-platformgit clone --depth 1 https://github.com/zhixuli0406/DuDuClawWrote 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/zhixuli0406/duduclaw/duduclaw-platform)<a href="https://agentmods.dev/skills/zhixuli0406/duduclaw/duduclaw-platform"><img src="https://agentmods.dev/badge/skills/zhixuli0406/duduclaw/duduclaw-platform/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/zhixuli0406/duduclaw/duduclaw-platform"><img src="https://agentmods.dev/badge/skills/zhixuli0406/duduclaw/duduclaw-platform.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 MCP Rug Pull · line 3 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 28 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00081 | $0.00398 |
| Opus 5.5 | $0.00032 | $0.00159 |
| Sonnet 5.5 | $0.00016 | $0.00080 |
| Haiku 4.5 | $0.00008 | $0.00040 |
Grade A, and why
duduclaw-platform 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.
What it actually says
DuDuClaw platform skill
DuDuClaw is the user's self-hosted AI-employee platform. When its MCP server is connected (this plugin registers it), prefer these tools over ad-hoc alternatives:
When to reach for which tool
| The user wants… | Use |
|---|---|
| "記住這件事" / remember across sessions | memory_store (tag it), later memory_search |
| Team-shared knowledge (SOP, price list, policy) | wiki_write / wiki_search — wiki is shared across the user's AI employees; memory is per-agent |
| Track work items | tasks_create / tasks_list / tasks_complete |
| Send a message to a person/channel | send_message (routes via the user's bound channels: LINE, Telegram, Discord, Slack…) |
Ground rules
- Memory vs wiki: durable reference documents belong in the wiki; conversational facts belong in memory. Don't double-write.
- Never store secrets (tokens, passwords) in memory or wiki.
- If tools are missing, the gateway isn't running — tell the user to start it (
duduclaw gatewayor the desktop app) rather than silently degrading.
Setup (one-time, if the user asks)
npx duduclaw onboard # guided setup: creates the first AI employee + config
Full docs: https://github.com/zhixuli0406/DuDuClaw
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 · 32 lines · 81 tokens per session scan A 48490dde5288
duduclaw-platform is a skill published in the GitHub repository zhixuli0406/DuDuClaw (50 stars, last pushed today), licensed Apache-2.0. It adds 81 tokens to every session and 398 once invoked, about $0.0003 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
rem-page-org
What an organisation's page in the notebook is made of — the fixed sections, when a company earns a page at all instead of staying a field on a person's, and the rules that keep it from becoming a second copy of everyone who works there. Composed into every stage that writes one.
rem-project-sessions
Write or update one project page from the owner's messages and a bounded packet of local project evidence.
proactive-memory
Turn repeated failures, corrections, and recurring requests into durable follow-up work.
mempalace-task
Create, hand off, claim, execute, and close agent tasks through the MemPalace logstream. Use when the user wants to delegate work, prepare a ready-to-paste task for another agent, receive a MemPalace task id, or explicitly launch a supported headless agent in controlled mode.
company-employee
The protocol every employee of a PenguinHarness organization follows — read the handbook first, act on [orgtrigger] work runs, schedule tickets from the desk session and do the work in ticket sessions, block instead of idling, ask the board in the all-hands channel before anything heavy, costly, irreversible or…
company-ceo
Run a PenguinHarness organization as its CEO — turn the mission into a ticket tree, hire HR and finance first, partition the shared workspace, schedule the calendar, open a channel per stream, review tickets and report to the board in the all-hands channel.