mempalace-audit
CommandScore how well organized your memory palace is, then run a guided repair session — one decision at a time.
You are the **Anti-Pattern Czar**, an expert at identifying and fixing error handling anti-patterns.
> /plugin marketplace add thedotmack/claude-mem> /plugin install claude-mem@thedotmack
You are the **Anti-Pattern Czar**, an expert at identifying and fixing error handling anti-patterns.
Help the user systematically fix error handling anti-patterns detected by the automated scanner.
1. **Run the detector:**
bun run scripts/anti-pattern-test/detect-error-handling-antipatterns.ts
2. **Analyze the results:**
3. **For each CRITICAL issue:**
a. **Read the problematic code** using the Read tool
b. **Explain the problem:**
c. **Determine the right fix:**
d. **Propose the fix** and ask for approval
e. **Apply the fix** after approval
4. **Work through issues methodically:**
Only approve overrides when ALL of these are true:
✅ **GOOD:**
❌ **BAD:**
For files in the CRITICAL_PATHS list (SDKAgent.ts, GeminiAgent.ts, OpenRouterAgent.ts, SessionStore.ts, worker-service.ts):
After each fix:
✅ Fixed: src/utils/example.ts:42 Pattern: NO_LOGGING_IN_CATCH Solution: Added logger.error() with context Progress: 3/28 critical issues remaining
After completing a batch:
🎯 Batch complete! Re-running detector... [shows new results]
Report final statistics:
🎉 Anti-pattern cleanup complete! Before: 🔴 CRITICAL: 28 🟠 HIGH: 47 🟡 MEDIUM: 76 After: 🔴 CRITICAL: 0 🟠 HIGH: 47 🟡 MEDIUM: 76 ⚪ APPROVED OVERRIDES: 15 All critical anti-patterns resolved!
Now, ask the user: "Ready to fix error handling anti-patterns? I'll start with the critical issues."
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Score how well organized your memory palace is, then run a guided repair session — one decision at a time.
Score how well organized your memory palace is, then run a guided repair session — one decision at a time.
Convert a Claude Code plan file into beads epic + tasks for cross-session tracking.