lean-vault

Run an autonomous research loop on a topic. Searches the web, synthesizes findings, and files everything into the wiki as structured pages.

Clip one or more webpages into the vault as clean source pages (via defuddle), then ingest them. Deliberate web egress — it fetches only the URLs you give it.

Stage text-layer PDFs into the vault and ingest them. Scanned (image-only) PDFs are reported and skipped, not ingested empty. No OCR.

Advance the active project by one task — read vault + project tasks.md, pick the next actionable task, execute it in this repo, record progress back to the vault.

Save the current conversation or a specific insight into the wiki vault as a structured note.

Parallel batch ingestion agent for the Obsidian wiki vault. Dispatched when multiple sources need to be ingested simultaneously. Processes one source fully (read, extract, file entities and concepts, update index) then reports what was created and updated. Use when the user says "ingest all", "batch ingest", or provides multiple files at once. <example>Context: User drops 5 transcript files into .raw/ and says "ingest all of these" assistant: "I'll dispatch parallel agents to process all 5 sources simultaneously." </example> <example>Context: User says "process everything in .raw/ that hasn't been ingested yet" assistant: "I'll use wiki-ingest agents to handle each source in parallel." </example>

Comprehensive wiki health check agent. Scans for orphan pages, dead links, stale claims, missing cross-references, frontmatter gaps, and empty sections. Generates a structured lint report. Dispatched when the user says "lint the wiki", "health check", "wiki audit", or "clean up". <example>Context: User says "lint the wiki" after 15 ingests assistant: "I'll dispatch the wiki-lint agent for a full health check." </example> <example>Context: User says "find all orphan pages" assistant: "I'll use the wiki-lint agent to scan for pages with no inbound links." </example>

Autonomous iterative research loop. Takes a topic, runs web searches, fetches sources, synthesizes findings, and files everything into the wiki as structured pages. Based on Karpathy's autoresearch pattern: program.md configures objectives and constraints, the loop runs until depth is reached, output goes directly into the knowledge base. Triggers on: "/autoresearch", "autoresearch", "research [topic]", "deep dive into [topic]", "investigate [topic]", "find everything about [topic]", "research and file", "go research", "build a wiki on".

Strip clutter from web pages before ingesting into the wiki. Removes ads, navigation, headers, footers, and boilerplate: leaving clean readable markdown that saves 40-60% tokens. Triggers on: defuddle, clean this page, strip this url, fetch and clean, clean web content before ingesting, strip ads, remove clutter, clean URL content, readable markdown from URL.

Advance the active project by one task. Reads vault state (hot.md + the project's tasks.md), selects the next actionable task, executes it in the current repo, then records progress back to the vault. Invoke with /next, or auto-invoke when the user says "do the next task" / "keep going on <project>".

Create and edit Obsidian Bases (.base files): Obsidian's native database layer for dynamic tables, card views, list views, filters, formulas, and summaries over vault notes. Triggers on: create a base, add a base file, obsidian bases, base view, filter notes, formula, database view, dynamic table, task tracker base, reading list base.

Write correct Obsidian Flavored Markdown: wikilinks, embeds, callouts, properties, tags, highlights, math, and canvas syntax. Reference this when creating or editing any wiki page. Triggers on: write obsidian note, obsidian syntax, wikilink, callout, embed, obsidian markdown, wikilink format, callout syntax, embed syntax, obsidian formatting, how to write obsidian markdown.

6 hooks across 4 events