# Memory Discipline

> trigger: repeated mistakes, rediscovered patterns, preferences, non-derivable facts. avoid: persisting file contents, git history, or task intermediates as memory.

- Skill: `open-coder-ai/memory-discipline` (Agent Skill)
- Install (CLI): `npx skillmds@latest add open-coder-ai/memory-discipline`
- Raw SKILL.md: https://api.skillmd.com/api/skills/open-coder-ai/memory-discipline/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Productivity
- Author: open-coder-ai (https://skillmd.com/u/open-coder-ai)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/open-coder-ai/memory-discipline

---


# Memory Discipline Rule

trigger: repeated mistakes, rediscovered patterns, preferences, non-derivable facts. avoid: persisting file contents, git history, or task intermediates as memory.

```
persist: decisions|preferences|non_derivable_facts; never_persist: file_contents|git_history|task_intermediates
extract(atomic_facts); consolidate(near_duplicate_facts); decay(stale); verify(memory) before_recommend
```

This skill is advisory: the client reading it has no mechanism to enforce it, and this policy stays advisory even when compiled by `chock` -- it ships rule text, not a blocking hook. See https://github.com/open-coder-ai/chock