workspace-navigator

workspace-navigator is a skill for Claude Code, Codex from zts212653/clowder-ai. It costs 50 tokens per session (2,896 once invoked), scanned A, original, MIT.

A workspace navigation method that turns a vague request such as “open the logs” or “show the design” into the exact local file or folder path.

In plain words
What is it for?
Finding and opening feature documents, design files, discussions, logs, source files, roadmap documents, and other workspace items.
Why use it?
It removes the need for the user to know where a document, source file, log, or design file is stored.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/user/cat-cafe/docs/VISION.md.

Good fit Finding and opening feature documents, design files, discussions, logs, source files, roadmap documents, and other workspace items.

Compare 6 skills from other repositories ↓
About the project

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.

zts212653/clowder-ai · 2,940 stars · on GitHub

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for workspace-navigator

README.md
[![agentmods](https://agentmods.dev/badge/skills/zts212653/clowder-ai/workspace-navigator/github.svg)](https://agentmods.dev/skills/zts212653/clowder-ai/workspace-navigator)
Your own site
<a href="https://agentmods.dev/skills/zts212653/clowder-ai/workspace-navigator"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/workspace-navigator/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.

agentmods 80×15 button for workspace-navigator

Your own site · 80×15
<a href="https://agentmods.dev/skills/zts212653/clowder-ai/workspace-navigator"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/workspace-navigator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,896 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00050 $0.02896
Opus 5 $0.00025 $0.01448
Sonnet 5 $0.00010 $0.00579
Haiku 4.5 $0.00005 $0.00290

Measured 5d ago against content hash 713252cb03e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

workspace-navigator scanned grade A with 1 finding 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 5d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

如果 MCP 工具不可用,先说明工具面缺失并按 F223 追踪;不要把手写第一方 `curl localhost` 当主路径。
cat-cafe-skills/workspace-navigator/SKILL.md · 204 lines

How it starts

The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Workspace Navigator

operator说"帮我打开XXX"时,你要自己找到路径,然后用 cat_cafe_workspace_navigate 让 Hub 右面板自动导航到那里。operator不会给你精确路径——这是你的活。

核心工作流(三步走)

Step 1: 意图解析 — operator想看什么?
  "帮我打开日志" → 日志文件/目录
  "看看 F131 的设计图" → F131 相关的 .pen 文件
  "打开那个 discussion" → 讨论文档

Step 2: 路径搜索 — 用你的工具找到精确路径
  用 glob/grep/read 找到文件的精确绝对路径;已有可靠 worktreeId 时也可用相对路径

Step 3: 调 typed MCP — 让 Hub 前端导航
  cat_cafe_workspace_navigate({
    path: "/精确/绝对/路径",
    action: "open",
    threadId: "当前 threadId(有就传)"
  })

  如 receipt 三工具同时可用且目标是文件,可改走下方的 revision-bound receipt 路径

Revision-bound consumption receipt(workspace-navigator pilot)

完整读完本文件后,如果当前工具面同时提供 cat_cafe_prepare_skill_consumptioncat_cafe_open_with_workspace_navigatorcat_cafe_dismiss_skill_consumption

cat_cafe_prepare_skill_consumption({ skillId: "workspace-navigator" })
  → cat_cafe_open_with_workspace_navigator({
      handle: "prepare 返回的 handle",
      path: "/精确/绝对/路径",
      threadId: "当前 threadId(有就传)"
    })
  1. cat_cafe_prepare_skill_consumption({ skillId: "workspace-navigator" })。返回的 state: prepared 只绑定当前 package revision、invocation 与 Workspace consumer,不是已应用收据
  2. 目标是要打开的文件时,把 handle 原样传给 cat_cafe_open_with_workspace_navigator({ handle, path, ... })。它固定调用既有 Workspace open consumer;只有 consumer 产生 deliveryStatus,服务端才会写 consumption: applied,猫不能单独自报。
  3. 若本次明确选择右侧「运行日志 → 查看日志」原生快捷入口,或读完后确认请求不属于 Workspace 导航,或本次目标是 pilot 尚未覆盖的目录 reveal,调 cat_cafe_dismiss_skill_consumption,reason 分别用 alternate_native_shortcut / outside_skill_scope

outcome 只回答这次 Workspace consumer 的投递四态或 not_applicable,不代表整项任务成功,也不证明 单个 skill 造成了任务结果。handle 过期、跨 invocation 重放或 package revision 已变化时,重新读当前 skill 并 prepare;不得拿旧 receipt 假绿。

完整读取仍是本 skill 的独立使用义务;receipt 本身不证明 package 曾被展示或读取,也不与既有 presentation/full-read 事件做前置 join。

如果 receipt 工具缺失,或返回 carrier_unsupported,照常完成导航任务,但明确记录 skill receipt: unsupported;不得从 ok:true、普通工具调用、task success 或旧的 skill-load 事件反推 applied|dismissed

Read the full file on GitHub · 204 lines

Changes

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.

  1. 5d ago Changed · +37 lines 713252cb03e6
  2. 9d ago First seen · 167 lines · 50 tokens per session scan A b98d39e10073

Subscribe to this mod's changes

workspace-navigator is a skill published in the GitHub repository zts212653/clowder-ai (2,940 stars, last pushed today), licensed MIT. It adds 50 tokens to every session and 2,896 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.