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 agentmods add skills/zts212653/clowder-ai/feat-lifecyclenpx skills add zts212653/clowder-ai --skill feat-lifecyclegit 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/feat-lifecycle)<a href="https://agentmods.dev/skills/zts212653/clowder-ai/feat-lifecycle"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/feat-lifecycle.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00112 | $0.10698 |
| Opus 5 | $0.00056 | $0.05349 |
| Sonnet 5 | $0.00022 | $0.02140 |
| Haiku 4.5 | $0.00011 | $0.01070 |
Grade A, and why
feat-lifecycle 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 — 578 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature Lifecycle
管理 Feature 从诞生到收尾：立项建追溯链、讨论沉淀决策、完成闭环同步。
核心知识
Feature vs Tech Debt：operator能感知变化 → Feature；只有开发者知道 → Tech Debt。不确定先记 TD。
追溯链架构：ROADMAP.md（热层）→ docs/features/Fxxx.md（温层，唯一入口）→ feature-discussions/research/plans（冷层）
演化关系：Evolved from（功能演进）/ Blocked by（硬依赖）/ Related（松耦合）
立项 (Kickoff)
触发：operator说"新功能"/"立项"、讨论收敛确认要做。不触发：还在探索 → collaborative-thinking Mode A；小修补 → TD。
开工前 Recall（F102 记忆系统）🔴
加载本 skill 后、动手前，先用记忆系统搜一下相关上下文：
search_evidence("{feature关键词}") # 找相关 feature / ADR
search_evidence("{topic}", scope="all") # 找历史讨论 + thread
为什么：防止重复造轮子、重蹈覆辙。记忆系统索引了 400+ docs + 所有 thread 摘要。
Step 0: 关联检测（内部 + 社区 issue 都必须做）🔴
分配 F 编号前，先跑关联检测，防止重复立项或把子任务误立为独立 feature：
- 扫描 BACKLOG + features/：
grep -i "{关键词}" docs/ROADMAP.md docs/features/*.md（或用search_evidence替代 grep） - 判定：
| 判定结果 | 处置 |
|---|---|
| 已有 Feature 的子任务/phase | 不立新号，挂到现有 Fxxx 下，issue 加 related: Fxxx |
| 已有 Feature 的相关需求 | 标记 related: Fxxx，由 maintainer 决定合并还是独立 |
| 全新独立需求 | 继续走 Step 1 分配 F 号 |
| 太小 / 纯 enhancement | 不立项，保留 enhancement 标签，不给 F 号 |
- 社区 issue 额外检查：
- 可行性：需求的数据源/依赖是否存在？
- 粒度：是独立 feature 还是现有 feature 的 UX polish？
- 回溯：feature doc 必须含
community_issue: #{issue号}字段
教训（F114/F115/F116 事故）：批量打标签 ≠ 审核通过。每个 issue 必须逐个过关联检测。
Step 1-5: 正式立项流程
5 步流程：
-
分配 ID：
grep -E "^\| F[0-9]+" docs/ROADMAP.md | tail -1，新 ID = 最大 + 1，三位数 -
创建聚合文件
docs/features/Fxxx-name.md（kebab-case 文件名）从标准模板创建：复制
../.cat-cafe-shared-refs/feature-doc-template.md中「模板正文」部分，替换占位符（{NNN}/{Feature Name}/{YYYY-MM-DD}等）。模板包含 Dashboard parser 所需的全部硬性格式。轻量 Feature（≤1 Phase）可省略 Timeline/Review Gate/Links/Key Decisions，但 Frontmatter + Status 行 + Why + Current State + What + User Journey（或
user_journey_exempt）+ AC + Dependencies 必须保留（全新能力的 Current State 写 "N/A（无既有基线）"，不是删段）。并在 spec 中补一节：
## 需求点 Checklist（模板见../.cat-cafe-shared-refs/requirements-checklist-template.md）
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 First seen · 578 lines · 112 tokens per session scan A 06054860d990
feat-lifecycle is a skill published in the GitHub repository zts212653/clowder-ai (2,906 stars, last pushed today), licensed MIT. It adds 112 tokens to every session and 10,698 once invoked, about $0.0006 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
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.