Strategy Constitutional Memory

A living knowledge base of hard-earned strategy lessons and banned code patterns — prevents repeating past mistakes across strategy iterations by scanning co...

This skill appears to do what it says: keep lessons and banned code patterns, scan strategy code, and generate context for an LLM. Before installing, decide where you want the memory stored (the default is a memory/ folder next to the code) and whether that storage could contain confidential strategy details; if so, use a private path, backups, and access controls. Review the persisted lessons.json / bans.json occasionally to ensure no sensitive code or credentials are being recorded, and confirm that your LLM usage of get_context() does not leak proprietary data to a third-party model you don't control. If you want added assurance, inspect the remainder of memory_system.py (the file appears truncated in the review snapshot) to confirm there are no network calls or unexpected subprocess invocations.

Type: OpenClaw Skill Name: strategy-constitutional-memory Version: 1.0.0 The skill bundle implements a 'Constitutional Memory' system designed to track lessons and banned code patterns for strategy development. The code (memory_system.py and cli.py) performs standard local file I/O for JSON storage and uses basic regex for pattern matching and text parsing, with no evidence of network activity, unauthorized file access, or command execution. The instructions in SKILL.md are consistent with the stated purpose of providing context to an AI agent to prevent repetitive coding errors.