fix: enforce workspace isolation to prevent agent pollution (#57) (#72)

Problem: After installing Agent Reach, agents may clone repos, create
files, or write output into the workspace directory, gradually polluting
the user's project. Over time this degrades the agent experience.

Fix:
- SKILL.md: add Workspace Rules section — never create files in workspace
- install.md: add Directory Rules table, explicit boundary about workspace
- install.md: all git clone commands now target ~/.agent-reach/tools/
- update.md: add workspace warning
- cli.py: install creates ~/.agent-reach/tools/ directory

All agent-facing docs now enforce: /tmp for temp, ~/.agent-reach/ for
persistent data, workspace stays untouched.

Co-authored-by: Panniantong <panniantong@users.noreply.github.com>

agent_reach/skill/SKILL.md

@@ -13,7 +13,19 @@ description: >
 
 # Agent Reach
 
-Install and configure upstream tools for 12+ platforms. After setup, call them directly — no wrapper layer.
+Install and configure upstream tools for 13+ platforms. After setup, call them directly — no wrapper layer.
+
+## ⚠️ Workspace Rules
+
+**Never create files, clone repos, or write output in the agent workspace.** Use these directories instead:
+
+| Purpose | Directory |
+|---------|-----------|
+| Temporary output (subtitles, downloads) | `/tmp/` |
+| Upstream tool repos | `~/.agent-reach/tools/` |
+| Config & tokens | `~/.agent-reach/` |
+
+Violating this will pollute the user's workspace and degrade their agent experience over time.
 
 ## Setup
 
@@ -277,7 +289,7 @@ asyncio.run(search())
 
 ```bash
 # Read a WeChat article (returns Markdown with images)
-cd /path/to/wechat-article-for-ai && python3 main.py "https://mp.weixin.qq.com/s/ARTICLE_ID"
+cd ~/.agent-reach/tools/wechat-article-for-ai && python3 main.py "https://mp.weixin.qq.com/s/ARTICLE_ID"
 
 # Run as MCP server (for AI agent integration)
 python3 mcp_server.py