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 opensource-opsgit 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/opensource-ops)<a href="https://agentmods.dev/skills/zts212653/clowder-ai/opensource-ops"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/opensource-ops/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/opensource-ops"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/opensource-ops.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 | $0.00109 | $0.03753 |
| Opus 5 | $0.00055 | $0.01877 |
| Sonnet 5 | $0.00022 | $0.00751 |
| Haiku 4.5 | $0.00011 | $0.00375 |
Grade A, and why
opensource-ops 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 3d 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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Open Source Ops — 外部 PR/issue 操作
SOP 位置: 本 skill 是
thread-orchestration在社区守门/外部 PR 场景下的子 workflow。 上一步:thread-orchestration（分发） | 下一步:request-review/receive-review/merge-gate
核心原则
- Server 不替你猜：F128 proposal runtime 不再推断 PR identity、作者角色、主仓采纳策略或任何实例私有同步策略。这些判断必须在拥有
cwd/ provider / provenance 上下文的 child-side 完成。 - Child thread 自己 grounding：进入子 thread 后，第一只猫必须显式加载本 skill，用 deployment 的 provider adapter（例如 GitHub 用
gh）把外部对象落到可验证的事实字段。 - 外部作者优先负责修复：默认把 finding 路由给外部作者；本地猫替作者改代码需要显式授权与 provenance。
- 反向溯源 fail-closed：
proposal source、projectPath、preferredCats、initialMessage里的 URL 都不能直接当 origin 证据；必须有独立的 provider 级验证与内部 provenance 搜索。
进入条件
在 child thread 中看到以下信号时加载本 skill：
title/reason/initialMessage出现外部 PR/issue URL 或owner/repo#NNN简写。- 任务明确是 review / triage / intake / advisory 之一。
- 需要与外部作者、CI、maintainer 交互。
Step 1: Grounding（落地 provider-neutral subject 与 author）
必须在动手判断之前完成。使用当前 deployment 的 provider adapter（例如 GitHub 场景用 gh）查询外部对象，产出以下事实字段；禁止从 thread title/reason 直接反推这些字段而不验证。
| 字段 | 类型 | 说明 |
|---|---|---|
providerSubject.kind |
pr / issue |
外部对象类型 |
providerSubject.fullName |
owner/repo |
外部目标仓库全名 |
providerSubject.number |
正整数 | PR/issue 编号 |
providerSubject.url |
URL | 对象 canonical URL |
providerSubject.headSha |
SHA（PR 必需） | formal review 的 exact-HEAD 锚点 |
providerSubject.state |
open / closed / merged 等 |
对象生命周期状态 |
verifiedAuthorIdentity |
字符串 | provider 返回的、已验证的作者 identity（如 GitHub login） |
authenticatedContributorIdentity |
字符串 | null |
当前本地认证 identity（如 gh auth status 返回的 active user）；无认证时为 null |
authenticatedRole |
maintainer / contributor / outsider / unknown |
当前 identity 对外部仓库的权限角色；无本地认证时按 outsider 处理 |
Fail-closed 分支：
verifiedAuthorIdentity是 bot / shared account / 无法解析 → 明确停住，标记author_kind: ambiguous，不继续 custody 判断，直到 operator 或 maintainer 显式确认。authenticatedContributorIdentity无法解析 → 按null处理，authenticatedRole降级为outsider。仅当工作流需要 mutating custody（review publication / merge / verdict）时才必须停住重新认证；纯 advisory / triage 审计可在匿名outsider角色下继续。- provider 查询失败（无网络、无权限、对象不存在）→ 停住，输出
unknown。
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.
- 3d ago Changed · +21 lines · +10 tokens per session e16f7572266c
- 9d ago First seen · 188 lines · 99 tokens per session scan A d0075183f7f6
opensource-ops is a skill published in the GitHub repository zts212653/clowder-ai (2,970 stars, last pushed yesterday), licensed MIT. It adds 109 tokens to every session and 3,753 once invoked, about $0.0005 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 2026-09-02.
Other skills, from other repositories
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
verify-behavior
Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…
github-contributor
End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating…
revdiff
Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…
oss-maintainer
Run an open-source project's issue/PR/release loop like a careful human maintainer — triage to root cause, absorb community PRs before duplicating them, gate every merge, ship honest releases, and thank the people doing your QA for free.