chore: refine platform policy and memory SKILL docs

nanobot/agent/context.py

@@ -58,6 +58,32 @@ Skills with available="false" need dependencies installed first - you can try in
         system = platform.system()
         runtime = f"{'macOS' if system == 'Darwin' else system} {platform.machine()}, Python {platform.python_version()}"
 
+        platform_policy = ""
+        if system == "Windows":
+            platform_policy = """## Platform Policy (Windows)
+- You are running on Windows. Shell commands executed via the `exec` tool run under the default Windows shell (PowerShell or cmd.exe) unless you explicitly invoke another shell.
+- Prefer UTF-8 for file I/O and command output. If terminal output is garbled/mojibake, retry with:
+  - PowerShell: `[Console]::OutputEncoding = [System.Text.Encoding]::UTF8; <command>`
+  - cmd.exe: `chcp 65001 >NUL & <command>`
+- Do NOT assume GNU tools like `grep`, `sed`, `awk` exist. Prefer Windows built-ins:
+  - Search text: `findstr /i "keyword" path\\to\\file`
+  - List files: `dir`
+  - Show file: `type path\\to\\file`
+- When in doubt, prefer the file tools (`read_file`, `list_dir`) over shell for portability and reliability.
+"""
+        elif system == "Darwin":
+            platform_policy = """## Platform Policy (macOS)
+- You are running on macOS. Prefer POSIX tools and UTF-8.
+- Use forward-slash paths. Prefer `ls`, `cat`, `grep`, `find` for filesystem and text operations.
+- When in doubt, prefer the file tools (`read_file`, `list_dir`) over shell for portability and reproducibility.
+"""
+        else:
+            platform_policy = """## Platform Policy (Linux)
+- You are running on Linux. Prefer POSIX tools and UTF-8.
+- Use forward-slash paths. Prefer `ls`, `cat`, `grep`, `find` for filesystem and text operations.
+- When in doubt, prefer the file tools (`read_file`, `list_dir`) over shell for portability and reproducibility.
+"""
+
         return f"""# nanobot 🐈
 
 You are nanobot, a helpful AI assistant.
@@ -71,6 +97,8 @@ Your workspace is at: {workspace_path}
 - History log: {workspace_path}/memory/HISTORY.md (grep-searchable). Each entry starts with [YYYY-MM-DD HH:MM].
 - Custom skills: {workspace_path}/skills/{{skill-name}}/SKILL.md
 
+{platform_policy}
+
 ## nanobot Guidelines
 - State intent before tool calls, but NEVER predict or claim results before receiving them.
 - Before modifying a file, read it first. Do not assume files or directories exist.

nanobot/skills/memory/SKILL.md

@@ -9,15 +9,20 @@ always: true
 ## Structure
 
 - `memory/MEMORY.md` — Long-term facts (preferences, project context, relationships). Always loaded into your context.
-- `memory/HISTORY.md` — Append-only event log. NOT loaded into context. Search it with grep. Each entry starts with [YYYY-MM-DD HH:MM].
+- `memory/HISTORY.md` — Append-only event log. NOT loaded into context. Search it with grep-style tools or in-memory filters. Each entry starts with [YYYY-MM-DD HH:MM].
 
 ## Search Past Events
 
-```bash
-grep -i "keyword" memory/HISTORY.md
-```
+**Recommended approach (cross-platform):**
+- Use `read_file` to read `memory/HISTORY.md`, then search in-memory
+- This is the most reliable and portable method on all platforms
 
-Use the `exec` tool to run grep. Combine patterns: `grep -iE "meeting|deadline" memory/HISTORY.md`
+**Alternative (if you need command-line search):**
+- **Linux/macOS:** `grep -i "keyword" memory/HISTORY.md`
+- **Windows:** `findstr /i "keyword" memory\HISTORY.md`
+- **Python (cross-platform):** `python -c "import re; content=open('memory/HISTORY.md', encoding='utf-8').read(); print('\n'.join([l for l in content.split('\n') if 'keyword' in l.lower()][-20:]))"`
+
+Use the `exec` tool to run these commands. For complex searches, prefer `read_file` + in-memory filtering.
 
 ## When to Update MEMORY.md