Clowder AI is a self-hosted workspace where AI agents from different model families work together as a persistent team, retaining identities, shared evidence, and memory across tasks. It is for people who want to coordinate multiple AI agents without repeatedly rebuilding their context.
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 zts212653/clowder-ai --skill custody-recognitiongit clone --depth 1 https://github.com/zts212653/clowder-aiWrote 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/zts212653/clowder-ai/custody-recognition)<a href="https://agentmods.dev/skills/zts212653/clowder-ai/custody-recognition"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/custody-recognition/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/zts212653/clowder-ai/custody-recognition"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/custody-recognition.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 | $0.00043 | $0.00958 |
| Opus 5 | $0.00022 | $0.00479 |
| Sonnet 5 | $0.00009 | $0.00192 |
| Haiku 4.5 | $0.00004 | $0.00096 |
Grade A, and why
custody-recognition 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 6d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Custody Recognition
This skill is the soft recognition policy at the ordinary conversation entry. It never owns work, attention, or scheduling truth. The exact source Message owns the offer/disposition; Task alone owns durable custody.
Read the exact source first
Use the current source message id. Read any source-bound custodyOfferV1 already supplied in context before choosing a branch:
- pending: do not create another offer or Task. Let the original rich choice stand.
- accepted + admitted/resumed: custody already exists. Do not prompt again; use the returned owner ref when continuing the work.
- accepted + needs_clarification: ask only the missing decision-changing question in this same conversation. After the answer, use cat_cafe_retry_custody_admission with the exact source revision, offer id, and complete Task contract. The server reuses the stored idempotency key.
- declined/dismissed: do not re-offer or admit. Continue conversationally unless the human later makes a new explicit entrustment.
Choose one branch
Explicit entrustment
Examples: “帮我接住”, “这件事你来跟”, or a direct request to own and finish an outcome.
Call cat_cafe_admit_entrusted_work immediately with:
- basis: explicit_entrustment;
- the exact source message ref;
- a stable idempotency key derived from that source ref;
- the intended outcome;
- a closure condition and expected signal;
- only source-backed time and Artifact refs.
When the source states an unambiguous deadline or review time, resolve it against the authenticated
invocation date/time and pass it in the top-level canonical time.businessDeadline or time.reviewBy
field with sourceRef: message:<sourceMessageId>. admission.timeHints may preserve the verbatim
wording, but it never becomes Task time and never makes the item appear in Schedule. If the time cannot
be resolved without changing the commitment, return needs_clarification instead of silently dropping
the time.
Do not show an offer after explicit entrustment. Return the compact typed receipt or the exact needs_clarification reason.
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.
- 6d ago Changed · +7 lines aaf10eb0cb51
- 7d ago First seen · 87 lines · 43 tokens per session scan A 747c9f385129
custody-recognition is a skill published in the GitHub repository zts212653/clowder-ai (2,970 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 958 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…