Self-correcting memory for LLM agents. A Claude Code plugin that learns from sessions, surfaces relevant memories, measures whether they're actually followed, and fixes the ones that aren't.
These files are toejough/engram's own configuration. They tell Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.
CLAUDE.md A 2,166 tok .claude/skills/openspec-apply-change/SKILL.md A 31 tok .claude/skills/openspec-archive-change/SKILL.md A 31 tok .claude/skills/openspec-explore/SKILL.md A 39 tok .claude/skills/openspec-propose/SKILL.md A 47 tok .claude/skills/openspec-sync-specs/SKILL.md A 38 tok .claude/skills/openspec-update-change/SKILL.md A 55 tok .claude/commands/commit.md A 12 tok .claude/commands/opsx/apply.md A 15 tok .claude/commands/opsx/archive.md A 13 tok .claude/commands/opsx/explore.md A 18 tok .claude/commands/opsx/propose.md A 21 tok .claude/commands/opsx/sync.md A 14 tok .claude/commands/opsx/update.md A 20 tok