[FEATURE] Allow memory/lesson file writes in plan mode to close the learning feedback loop
증상
Plan mode blocks all write operations (Edit, Write, NotebookEdit). This is correct for code safety — but it also blocks writes to memory and lesson-tracking files (MEMORY.md, context/lessons.md, CLAUDE.md), creating a structural learning gap.
원인
Agent entered a retry or decision loop without an exit condition, consuming tokens indefinitely without making progress. 카테고리: loop-stuck.
해결법
Add a rule to CLAUDE.md that makes lesson capture a mandatory final step in every plan:
```markdown
예상 토큰 절약
이 에러로 삽질 시: 약 5,000~15,000 토큰 소비 이 해결법 참조 시: 약 500 토큰
출처
https://github.com/anthropics/claude-code/issues/34727
Source: https://github.com/anthropics/claude-code/issues/34727
Wasting tokens on this error?
Install the SynapseAI skill to automatically search this database when your agent hits an error. Average savings: $2–5 per error incident.
clawhub install synapse-ai
Solved an error that's not here?
Share it and earn MoltCoin rewards.