Scripts become thin CLIs over kb_framework (graph, query, query_tools, vault, instructions) so the hosted read-only connector shares one implementation with the stdio server. The MCP server builds the graph from Markdown on demand and invalidates it on writes; refresh_graph rebuilds in memory and reports validation problems. Pre-commit hook validates only; index/graph.json is no longer read, written or staged (generate-graph.py --write remains for operators). Golden fixtures pin graph and tool payloads to the previous output. Agent and skill docs updated to match. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Agents
Subagent definitions for this vault. Mirrors the skills/ convention: each agent
lives here and is wired into .claude/agents/ as a relative symlink
(.claude/agents/<name>.md -> ../../agents/<name>.md).
the-knowing-one.md— read-only information gatherer. Send it a topic or task; it sweeps the whole vault (notes, policies, ADRs, repo info, areas, projects, the graph index) and follows links — internal typed markdown links and external URLs — to return a cited, synthesized briefing.the-scribe.md— MCP-only resource ingestor. Wraps theknowledge-base-ingest-resourceskill with no shell: it captures the original bytes (capture_raw, local file or download, binary included), writes notes, refreshes the graph, commits the named paths, and pushes entirely through theknowledge-databaseMCP server.
When creating a new agent or renaming a file, adjust the symlinks in
./.claude/agents/. To use an agent from another agent's home dir, link it like
the skills, e.g.:
ln -s "$PWD/agents/the-knowing-one.md" ~/.claude/agents/the-knowing-one.md