diff --git a/bin/claude-code b/bin/claude-code
index 59788a1..7246f63 100755
--- a/bin/claude-code
+++ b/bin/claude-code
@@ -1,19 +1,10 @@
-#!/bin/bash
-# Wrapper that sets ANTHROPIC_API_KEY from OpenClaw's auth config
-export ANTHROPIC_API_KEY=$(python3 -c "
-import json
-with open('/home/openclaw/.openclaw/agents/main/agent/auth-profiles.json') as f:
-    data = json.load(f)
-for key, profile in data.get('profiles', {}).items():
-    if 'anthropic' in key:
-        print(profile.get('token', ''))
-        break
-" 2>/dev/null)
+#!/usr/bin/env bash
+# Claude Code CLI wrapper
+# Usage: claude-code "task description" [working-dir]
+set -euo pipefail
 
-if [ -z "$ANTHROPIC_API_KEY" ]; then
-    echo "Error: Could not extract Anthropic API key from auth-profiles.json"
-    exit 1
-fi
+TASK="${1:?Usage: claude-code <task> [working-dir]}"
+WORKDIR="${2:-$(pwd)}"
 
-export PATH=$PATH:/usr/local/go/bin
-exec claude "$@"
+cd "$WORKDIR"
+exec claude -p "$TASK" --allowedTools "Edit,Write,Bash"
diff --git a/debug_health_orb.png b/debug_health_orb.png
new file mode 100644
index 0000000..93eea36
Binary files /dev/null and b/debug_health_orb.png differ
diff --git a/debug_mana_orb.png b/debug_mana_orb.png
new file mode 100644
index 0000000..1f0077c
Binary files /dev/null and b/debug_mana_orb.png differ
diff --git a/projects/iso-bot b/projects/iso-bot
index 67f2e55..0716aeb 160000
--- a/projects/iso-bot
+++ b/projects/iso-bot
@@ -1 +1 @@
-Subproject commit 67f2e5536aba342d3108cecdac29d3839cbd6dac
+Subproject commit 0716aeb5e13a100a632eff255e33f840240f0715
diff --git a/skills/coding-agent/NOTES.md b/skills/coding-agent/NOTES.md
new file mode 100644
index 0000000..5f7eb05
--- /dev/null
+++ b/skills/coding-agent/NOTES.md
@@ -0,0 +1,50 @@
+# Claude Code Usage Notes
+
+## Golden Rule
+**User gives task → spawn sub-agent → sub-agent runs Claude Code → sub-agent verifies → user gets ONE summary message. No play-by-play.**
+
+## How to Use Claude Code
+
+### Via Sub-Agent (preferred for complex tasks)
+```
+sessions_spawn with task like:
+"Run Claude Code to [task]. Working dir: /path/to/project.
+After Claude Code finishes, verify the changes compile and make sense.
+If not, run Claude Code again with fixes. Commit and push when done."
+```
+
+### Direct (simple tasks only)
+```bash
+cd /path/to/project
+claude -p "task description" --allowedTools "Edit,Write,Bash"
+```
+
+## Key Facts
+- **Default model**: Opus 4.6 (no override needed)
+- **Auth**: OAuth login already completed, no API key needed
+- **Allowed tools**: Always pass `--allowedTools "Edit,Write,Bash"`
+- **Timeout**: Claude Code can take 5-20 minutes for complex tasks. Don't micromanage.
+- **Hanging**: Sometimes streams hang after ~10-15 min. Sub-agent can detect this and retry.
+- **PTY mode**: Use `pty=true` when running via exec
+
+## Sub-Agent Task Template
+```
+Run Claude Code CLI in /path/to/project to do the following:
+
+[TASK DESCRIPTION]
+
+Steps:
+1. Run: cd /path/to/project && claude -p "[task]" --allowedTools "Edit,Write,Bash"
+2. Wait for completion (up to 20 min, check if process is still alive periodically)
+3. If it hangs (no file changes for 10+ min), kill and retry once
+4. After completion, verify: go build / npm build / etc
+5. If build fails, run Claude Code again with the error
+6. Commit and push when everything works
+7. Report summary of all changes made
+```
+
+## Anti-Patterns
+- ❌ Polling every 30 seconds and reporting progress
+- ❌ Sending WhatsApp messages during the process
+- ❌ Reading every file before/after to narrate changes
+- ✅ Fire and forget, verify at end, report once