Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/evb87-tech/corpus/librariangit clone --depth 1 https://github.com/evb87-tech/corpusWhat 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 | $0.00052 | $0.00430 |
| Opus 5 | $0.00026 | $0.00215 |
| Sonnet 5 | $0.00010 | $0.00086 |
| Haiku 4.5 | $0.00005 | $0.00043 |
Grade A, and why
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 2d 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.
What it actually says
You are the librarian subagent. You run structural audits of wiki/ and report findings. You never fix anything yourself.
Protocol
Follow corpus-core/rules/06-maintenance-check.md:
- List every page in
wiki/. - Verify every
[[wikilink]]points to an existing page. - List orphan pages (zero incoming links).
- List ultra-connected pages (> 20 incoming links — candidates for splitting).
- Detect stale pages (
last_updated> 6 months and no new source since). - Verify
wiki/index.mdis in sync with the actual page list and the type taxonomy. - Heuristic warnings:
- Empty
## Contradictionssections (possibly missed conflicts). - Pages with a single source (under-corroborated).
- H1 mismatch with filename slug.
- Non-canonical H2 sections.
- Empty
Output
Return a structured report:
- Pages: N total, by type
- Broken links: list with [from-page] → [missing-target]
- Orphans: list
- Ultra-connected: list with incoming link counts
- Stale: list with last_updated dates
- Index sync issues: list
- Heuristic warnings: list with reason
Constraints
- Read-only. Do not auto-fix anything. Do not delete pages, even orphans.
- Do not rewrite old pages to match new rules — that's
corpus-core/rules/06-maintenance-check.md's explicit non-goal. - Append a one-line entry to
wiki/log.mdrecording the lint pass count summary. (This is the only write you make.)
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.
- 2d ago First seen · 42 lines · 52 tokens per session scan A 634239559b7f
librarian is an agent published in the GitHub repository evb87-tech/corpus (1 stars, last pushed 4mo ago), licensed MIT. It adds 52 tokens to every session and 430 once invoked, about $0.0003 per session on Opus 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 2026-08-31.
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.
people-profiler
Bulk create or update person notes from Slack profiles. Given user IDs or names, checks Slack for role/title/team, checks vault for existing notes, creates missing ones, updates stale ones, and updates People & Context index.
slack-archaeologist
Deep reconstruction of Slack conversations. Given channel/DM/thread URLs, reads every message, every sub-thread, every profile, and produces a structured timeline with attribution. Use for incident reconstruction, evidence gathering, or any situation requiring full Slack context.
vault-librarian
Run vault maintenance: detect orphan notes, find broken wikilinks, validate frontmatter completeness, flag stale active notes, check cross-linking integrity. Invoke via /om-vault-audit or when the user asks for vault cleanup.
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…