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 writing-plansgit 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/writing-plans)<a href="https://agentmods.dev/skills/zts212653/clowder-ai/writing-plans"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/writing-plans/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/writing-plans"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/writing-plans.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 | $0.00069 | $0.01888 |
| Opus 5 | $0.00034 | $0.00944 |
| Sonnet 5 | $0.00014 | $0.00378 |
| Haiku 4.5 | $0.00007 | $0.00189 |
Grade A, and why
writing-plans 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.
How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Plans
Overview
将 spec/需求拆分为分步实施计划。写清楚每步改哪些文件、代码、测试、怎么验证。DRY. YAGNI. TDD. Frequent commits.
Announce at start: "I'm using the writing-plans skill to create the implementation plan."
Context: Write the plan on main before opening a feature worktree. After the plan is committed, continue to worktree and then tdd.
开工前 Recall（F102 记忆系统）🔴：写计划前先搜相关历史——search_evidence("{feature}") 找相关 spec/ADR/讨论，避免重复造轮子。
Save plans to: feature-specs/YYYY-MM-DD-<feature-name>.md
Straight-Line Check (A→B, No Detour)
Before splitting steps, do this first:
- Pin the finish line: one-sentence B definition + acceptance criteria + "what we're NOT building"
- Define terminal schema: interfaces / types / data structures of the final form — steps are built around this, not throwaway scaffolding
- Every step passes three questions:
- Will this step's output stay in the final system as-is (extend only, no rewrite)? → Yes = on the line; No = detour
- What can we demo/test after this step? (no verifiable evidence = detour)
- If we remove this step, what specific cost does it add to reaching B? (can't articulate = detour)
- Pure exploration = explicit Spike (time-boxed + output is a decision/conclusion, not a deliverable)
Steps are internal implementation rhythm, NOT delivery batches. The deliverable to the user is a complete feat matching the full spec — not a step's output. Do not expose intermediate steps as "验收点" to the user.
Stateful Object Gate（F229 PR-A1 20 轮教训）🔴
Plan 涉及有生命周期的状态对象（thread 标记 / carrier / session / 持久 config / cache / 索引 / 注册表）时，「功能描述 + 幂等测试点」不够——那是把状态机的边留给 reviewer 逐轮补（PR #2202 实测：4 P1 + 16 P2 全是同一对象的状态转移边——crash window / restore 复活 / deleted-list 漏过滤 / 并发 race / self-heal，打了 20 轮才合入）。
Census 先行（F229 A3a 二次教训 2026-06-11）：gate 第一步是普查——列出 plan 涉及的全部有生命周期对象再逐个三件套。特别注意"复用现有 API"场景下的新消费侧状态（轮询循环、发送闸门、到达判定器都是状态机）。漏报对象 = gate 形同虚设：F229 A3b 三对象三件套齐全，A3a 的 ConversationSendCycle 漏普查 → 云端同型 5 轮逐边补课。
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 · 161 lines · 69 tokens per session scan A 035e4d66932a
writing-plans is a skill published in the GitHub repository zts212653/clowder-ai (2,940 stars, last pushed yesterday), licensed MIT. It adds 69 tokens to every session and 1,888 once invoked, about $0.0003 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
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…