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 convention-graph-discoverygit 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/convention-graph-discovery)<a href="https://agentmods.dev/skills/zts212653/clowder-ai/convention-graph-discovery"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/convention-graph-discovery/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/convention-graph-discovery"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/convention-graph-discovery.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 | $0.00157 | $0.01656 |
| Opus 5 | $0.00078 | $0.00828 |
| Sonnet 5 | $0.00031 | $0.00331 |
| Haiku 4.5 | $0.00016 | $0.00166 |
Grade A, and why
convention-graph-discovery 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 10d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Convention Graph Discovery
价值门禁 / Why This Is a Skill
这是 Clowder AI 特有的方法论：把 repo 里的“约定层关联”（MCP tool、skill trigger、route、workflow callback、配置驱动注册）画成带 provenance/freshness 的图。它不是通用 AST 教程，也不是让猫依赖 codegraph/GitNexus；它把 F242 的 dogfood 经验沉淀成未来进 repo 的第一步。
核心知识 / Overview
LSP 看符号，grep 看文本；约定图看“这个 repo 的规矩”。每条边必须能回答三件事：它从哪个 source span 来、当前图新不新鲜、漏识别的 gap 在哪。
When to Use
用在：
- 刚进入陌生 repo，需要先摸清“改 X 会影响谁”。
- 改动触及配置/注册/manifest/route/callback 等约定层，不只是函数调用。
- 改 MCP tool schema/name、skill manifest、FastAPI/API route、workflow callback 前，需要先找约定层消费方。
- F242 / Convention Graph Layer 相关实现、dogfood、review。
不要用在：
- 已经能用 LSP 精确跳转的普通函数调用。
- 只想找文档或历史讨论（用 memory-navigation / memory-search-best-practices）。
- 想把 codegraph/GitNexus 当外部依赖直接接入。
- 只是 cat-cafe 自家 extractor 的硬编码搬运。
流程 / Discovery Protocol
- 定边界：写清 repo、目标问题、要验证的 convention domain。例：MCP tool 消费方、FastAPI route、skill trigger。
- 找显式锚点：优先找名字/ID/typed import/config key/manifest field。禁止 name-only 跨语言合并。
- 定义 domain：列
domainId、node kinds、edge kinds、extractor inputs、invalidation scope、negative fixtures。 - 写 extractor：先用最小 fixture TDD，产出 nodes / edges / gaps。每条 edge 带 extractor/version/sourceFile/sourceLine/confidence。
- 接引擎：记录 index commit + indexed file hashes；查询必须带 freshness，pending changes 直接标 stale。
- 对比基线：用 grep/LSP 或人工查证对比，记录它们漏了什么、约定图多解释了什么。
- 报 gap：发现框架或约定但没覆盖时输出 gap/unknowns，不能静默 0 命中。
Product Entry / Commands
在 Clowder AI repo 根目录，先重建当前 repo 的图：
pnpm convention-graph:index -- --repo .
查某个 MCP tool 的约定层消费方：
MCP_TOOL_NAME=replace_with_tool_name
pnpm convention-graph:code-consumers -- --repo . --domain mcp-tool --kind mcp_tool --name "$MCP_TOOL_NAME"
查某个 skill manifest 的触发/消费方（CLI 接受 skill 作为 skill_manifest 的人类友好别名）：
SKILL_NAME=replace_with_skill_name
pnpm convention-graph:code-consumers -- --repo . --domain skill-manifest --kind skill --name "$SKILL_NAME"
输出是 JSON，包含 targets、consumers、每条 edge 的 provenance，以及 freshness。如果 freshness.stale=true，这次查询只能当 stale 证据；先重跑 convention-graph:index，再决定影响面。
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.
- 10d ago First seen · 117 lines · 157 tokens per session scan A 165bcd35d5cd
convention-graph-discovery is a skill published in the GitHub repository zts212653/clowder-ai (2,956 stars, last pushed today), licensed MIT. It adds 157 tokens to every session and 1,656 once invoked, about $0.0008 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…