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 skills add kengo006/alexandria --skill librariangit clone --depth 1 https://github.com/kengo006/alexandriaWrote 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/skills/kengo006/alexandria/librarian)<a href="https://agentmods.dev/skills/kengo006/alexandria/librarian"><img src="https://agentmods.dev/badge/skills/kengo006/alexandria/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/skills/kengo006/alexandria/librarian"><img src="https://agentmods.dev/badge/skills/kengo006/alexandria/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 | $0.00079 | $0.00301 |
| Opus 5 | $0.00039 | $0.00151 |
| Sonnet 5 | $0.00016 | $0.00060 |
| Haiku 4.5 | $0.00008 | $0.00030 |
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 10d 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
Librarian (wrapper)
Authority lives in the master file — this wrapper only loads it.
- Read
governance/role-division.md. - Read
roles/librarian.md— the four gates, error taxonomy, protocols. - Read the format layer:
obsidian/note-schema.md,obsidian/vault-structure.md,obsidian/wikilinks-and-mocs.md. - Orient:
notes/vault-map.md; pending errata queue if one exists.
Digest of red lines (master wins):
- G1: no note is written or rewritten without reading the source. The "reconstruct from general knowledge" fallback is banned by name.
- One-before-many; filename verification before filing; idempotent scripts with dry-runs.
- Content-depends-on-source work is strictly serial.
- "Done" requires the three-part completion report (verified / unverified / skipped) — never the bare word.
- Deletions are moves to the trash zone; nothing is permanently deleted.
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.
- 10d ago First seen · 21 lines · 79 tokens per session scan A d270cd70b029
librarian is a skill published in the GitHub repository kengo006/alexandria (5 stars, last pushed 17d ago), licensed MIT. It adds 79 tokens to every session and 301 once invoked, about $0.0004 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 skills, from other repositories
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
doc-reader
Read any common document/data file — PDF, Word (.docx), Excel (.xlsx/.xls), PowerPoint (.pptx), images (OCR), CSV/TSV, plain text, JSON/YAML/TOML, HTML/XML, and most source-code files. Use the readdocument tool.
patent-reader
A plain-language reader for Chinese patents that turns a publication number or PDF into notes, diagrams, and an Obsidian entry. Obsidian is a note-taking app that stores linked Markdown files.
oma-pdf
Convert PDF files to Markdown using opendataloader-pdf. Extracts text, tables, headings, lists, and images with correct reading order. Use for PDF parsing, PDF to Markdown conversion, document extraction, and AI-ready data preparation.
pandic-office
Convert Markdown to PDF (or DOCX/EPUB/HTML) using the pandoc CLI. Use when asked to produce a PDF report, brief, summary, or any document where the input is Markdown and the output should be a polished, paginated file.
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and…