Read a file or directory listing from the AI knowledge vault.

Write or append to a file in the AI knowledge vault.

Full-text search (SQLite FTS5 porter stemming) scoped to this project. Structured mode still matches frontmatter.

Get the context document for a project. Auto-detects project from CWD if not specified.

Scan a git repo and generate a draft context.md. Returns the draft — does NOT write to vault. Human reviews before committing.

Log an architectural/design decision to the project's decisions directory.

Manage project tasks. Supports add, list, update, and board (kanban) views. Tasks are stored as individual files in projects//tasks/.

Capture and query learnings. Learnings persist discoveries across sessions. Stored as individual files in projects//learnings/.

Start or continue a brainstorm document for a project.

Register, update, or query active agent sessions for multi-agent coordination. On complete, persists a session note to the vault.

Archive or delete stale vault content based on retention policies. Use mode='dry-run' first to preview.

Show content statistics for a project — file counts, task breakdown, growth monitoring.

Get resume context for continuing work — recent sessions, interrupted work, in-progress tasks, suggested next steps. Call this at session start to understand what happened before.

Mark a vault item (ADR, learning, etc.) as deprecated with an optional reason.

Initialize superskill for the current project. Detects stack, indexes the in-repo catalog, builds the knowledge graph. Does not scrape skills.sh.

Show superskill knowledge graph state: loaded skills, weights, recent sessions.

Route a task to curated in-repo packs (code/review/security/ops/devops). Lazy: only matching language + phase. Does not scrape skills.sh.

Install skills from a GitHub repo (e.g. owner/repo or full URL). Clones the repo, discovers SKILL.md files, and copies them to the local skill directory.

List skills installed locally from GitHub repos.

Remove an installed skill by name.

Create a forward link between two vault notes. Appends a [[wikilink]] to the source note, enabling graph_related to discover the connection.

Extract decisions, learnings, or other items from a source document into individual vault files. Each extracted item gets its own file with a backlink to the source.

Related notes via the FTS/edge index (related frontmatter + wikilinks), jailed to this project.

Rebuild this project's SQLite FTS5 + edges index from markdown. Source of truth stays the files.

Write knowledge-graph.html (browser) and knowledge-graph.canvas (open in Obsidian). Same edges as the FTS index.

Regenerate the knowledge graph HTML and drive system Chrome to click nodes and read the panel. In-harness QA, not a plugin.

Search the current project's vault only. Cross-project search is denied.

Snapshot current git state (branch, dirty files, last commit) into the vault. Helps avoid repeating repo discovery across sessions.

Store and query stable environment facts for a project (e.g., auth backend, env file locations, local URLs, required env vars). Not for secrets — use cred_refs for that.

Store pointers to where credentials are documented (not the credentials themselves). E.g., 'Django admin creds are in tests/live/test_all_endpoints.py'.

Manage rollback checkpoints. Store commit hashes with purpose/scope so rollback is safer. Mark when follow-up work starts after a checkpoint.

Batch-capture multiple insights from a conversation into individual vault items. Each item gets its own file with auto-numbering. Supports any content type (learning, decision, adr, prd, research, etc.).

Get pre-filled templates for common vault item types (adr, prd, decision, learning, spec, rfc, roadmap, competitive-analysis, incident, research, vision, strategy). Use to scaffold new documents.