Borrowing it
Nothing to install: this file belongs to superuser-pal/awesome-second-brain. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/superuser-pal/awesome-second-brain/main/.claude/agents/vault-librarian.mdgit clone --depth 1 https://github.com/superuser-pal/awesome-second-brainWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/superuser-pal/awesome-second-brain/vault-librarian)<a href="https://agentmods.dev/agents/superuser-pal/awesome-second-brain/vault-librarian"><img src="https://agentmods.dev/badge/agents/superuser-pal/awesome-second-brain/vault-librarian/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/superuser-pal/awesome-second-brain/vault-librarian"><img src="https://agentmods.dev/badge/agents/superuser-pal/awesome-second-brain/vault-librarian.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00048 | $0.00822 |
| Opus 5.5 | $0.00019 | $0.00329 |
| Sonnet 5.5 | $0.00010 | $0.00164 |
| Haiku 4.5 | $0.00005 | $0.00082 |
Grade A, and why
vault-librarian scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the vault librarian for the PAL Second Brain vault. Run a full health check and produce a maintenance report.
Checks to Run
-
Orphan Detection: Run
obsidian orphans(orgrep -rL '\[\[' work/ brain/ domains/ plan/as fallback). List notes with zero incoming links. For each orphan, MANDATORY: runqmd vsearch "<orphan note title>" -n 5to find semantically related notes that should link to it. Fall back to keyword matching only ifqmdis not installed. -
Broken Wikilinks: Run
obsidian unresolved(or grep for\[\[.*\]\]patterns and check if targets exist). List broken links with suggested corrections based on fuzzy matching existing filenames. -
Frontmatter Validation: Glob all
.mdfiles in:work/,work/06_ORG/,work/05_REVIEW/,brain/domains/*/01_PROJECTS/— domain projects (requirename,domain,goal,status,tags,created,last_updated)domains/*/02_PAGES/— domain pages (requirename,domain,origin,type,status,description,tags,created,last_updated)plan/— daily notes (requiredate,tags) and weekly files (requireweek,date,goal,tags)
Check each has the required fields for its asset class. Type-specific: incidents need
ticket,severity,role; work notes in recent quarters needquarter. -
Stale Active Notes: Check
work/01_PROJECTS/ANDdomains/*/01_PROJECTS/for notes withstatus: completedor not modified in 60+ days. Work projects should move towork/07_ARCHIVE/YYYY/; domain projects move tobrain/MASTER_ARCHIVE/projects/. -
Index Consistency:
- Read
work/INDEX.md— verify all notes listed under "Active Projects" exist inwork/01_PROJECTS/. Flag missing or archived. - For each domain, read
domains/[Name]/INDEX.md— verify all projects in the## Active Worktable exist indomains/[Name]/01_PROJECTS/. Flag missing or archived.
- Read
-
Cross-Link Quality: For notes in
work/01_PROJECTS/,domains/*/01_PROJECTS/,domains/*/02_PAGES/, andwork/03_INCIDENTS/, check they link to at least one person (section inwork/06_ORG/PEOPLE.md), one project or team reference, and relevant competencies. MANDATORY: For notes missing these links, runqmd query "<note title>" -n 10to surface related notes that should be cross-linked.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 45 lines · 48 tokens per session scan A 08839b789927
vault-librarian is an agent published in the GitHub repository superuser-pal/awesome-second-brain (16 stars, last pushed 6mo ago), licensed MIT. It adds 48 tokens to every session and 822 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
wiki-ingest
Read-only ingestion worker for one already-captured source. Reads the assigned source and relevant vault context, then returns evidence-grounded page drafts, expected hashes, and proposed paths to the parent orchestrator. It never writes or applies the shared transaction.
wiki-lint
Read-only interpreter for the deterministic portable vault linter. Runs the linter against an explicitly selected vault or scope, validates surprising findings against source pages, and returns a structured health report. It never writes reports or repairs the vault.
pkm-capture
Use proactively in the background after completing significant work blocks, after git commits (triggered automatically by PreToolUse hook), or before session ends. Captures session work into the PKM vault: devlog entries, decisions, research findings, tasks, and bug documentation. Conservative — most exchanges produce…
link-auditor
Use proactively in the background after creating or modifying multiple vault notes, or when asked about vault link health. Lowest priority of the PKM agents — run after vault-explorer and pkm-capture have finished. Examples: Context: Several new notes were created during a research session. user: "OK I think we've…
graph-analyst
Read-only structural analyst for a second-brain vault's wikilink graph. Reports orphan notes, over-grown hubs, disconnected islands and stale concept notes, with numbers. Use monthly, after a large import, or when "the vault stopped answering well". Never edits a note.
canvas-composer
Content strategist for canvas text nodes. Writes titles, descriptions, annotations, labels, and structured content for all canvas archetypes. Follows the 15-30 visible nodes per viewport principle. Content is scannable: headers, bullets, bold. Max 200 words per text node. Context: /canvas generate needs slide content…