Skill Claude CodeCodex
Handle imported and extracted material correctly. Use when placing content in Evidence/, importing web pages or docs, recording captures, or deciding what is and isn't canonical.
Skill Claude CodeCodex
Backfill project memory from existing repo evidence (codebase, docs, configs, git history, tasks, sessions, agent traces). Use when the memory tree is new or sparse and the project has existing history.
Skill Claude CodeCodex
Compact and prune the memory tree when it grows large or stale. Use when Memory/MEMORY.md grows noisy, branch notes exceed 150 lines, or when explicitly asked to clean up memory.
Skill Claude CodeCodex
Read on session start. Manages adaptive durable memory across conversations. Use when reading or writing curated memory under agent-knowledge/Memory/.
Skill Claude CodeCodex needs its repo
Write memory notes that are pleasant in Obsidian without requiring Obsidian. Optional enhancement skill. Use when the user has Obsidian open alongside their agent workflow and wants better vault navigation.
Skill Claude CodeCodex
Infer a project's natural ontology from the actual repo. Use when determining what memory branches to create, how to name them, and how to decompose the project into focused domains.
Skill Claude CodeCodex needs its repo
Write high-quality, stable memory notes. Use when creating or updating notes in agent-knowledge/Memory/ and you want specific guidance on format, quality, and what to include.
Skill Claude CodeCodex
Bootstrap an adaptive project knowledge tree. Use when agent-knowledge/Memory/MEMORY.md is missing, broken, or too generic.
Skill Claude CodeCodex
Read on session start. Tracks work progress in session files during conversations. Use when recording milestones, decisions, blockers, or when the session-start hook creates a session file.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: