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 magnus919/agent-skills --skill openlibrarygit clone --depth 1 https://github.com/magnus919/agent-skillsWrote 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/magnus919/agent-skills/openlibrary)<a href="https://agentmods.dev/skills/magnus919/agent-skills/openlibrary"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/openlibrary/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/magnus919/agent-skills/openlibrary"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/openlibrary.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00113 | $0.03262 |
| Opus 5 | $0.00056 | $0.01631 |
| Sonnet 5 | $0.00023 | $0.00652 |
| Haiku 4.5 | $0.00011 | $0.00326 |
Grade A, and why
openlibrary scanned grade A with 1 finding 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
(`curl -L`; `requests` does by default) or they parse an HTML redirect page. How it starts
The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
openlibrary — Book Metadata from Open Library
Query Open Library's 50M+ record catalog over its public HTTP API: search works and authors, walk the edition/work/author graph by ISBN or OLID, enumerate editions, and read community ratings. No API key exists; everything here is a keyless GET.
Setup
Nothing to authenticate: the public Open Library API requires no API key for reads. There is no token, no registration step, no lazy-auth dance.
# Optional etiquette: identified User-Agent gets ~3x rate budget (~3 req/s vs ~1)
export OL_EMAIL="[email protected]"
Requires Python 3.8+ and requests only. --help and --dry-run work with no
environment at all. Write endpoints exist upstream but require an authenticated
Internet Archive session and are effectively internal — treat this surface as
read-only.
Three hosts matter and they serve different things:
| Host | Serves |
|---|---|
openlibrary.org |
metadata JSON: search, records, ratings |
covers.openlibrary.org |
cover images + author photos (separate service) |
archive.org |
scan content / bulk dumps (redirect targets) |
Essential Commands
find books — search
openlibrary search --query "dune" # relevance order
openlibrary search --query "dune" --sort editions # most editions first
openlibrary search --query "dune" --sort new # newest first
openlibrary search --query "foundation" --lang fr # prefer French editions
openlibrary search --query "dune" --limit 5 --offset 10 # paginate
openlibrary search --query "dune" --json # machine-readable
Results carry title, authors, first_publish_year, edition count, and the work
key (/works/OL…W) that feeds the other commands. The CLI validates --sort
choices client-side because an unknown sort value makes the server return a
plain-text HTTP 500.
find people who write — author search
openlibrary search-authors --query "asimov" # name candidates
openlibrary search-authors --query "le guin" --limit 5
openlibrary search-authors --query "asimov" --json # includes top_work, work_count
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 262 lines · 113 tokens per session scan A 67b58138800b
openlibrary is a skill published in the GitHub repository magnus919/agent-skills (75 stars, last pushed yesterday), licensed MIT. It adds 113 tokens to every session and 3,262 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
canvas-course-ops
Use this skill for course, assignment, and LMS-style operational tasks that need clear status tracking and student-safe messaging.
odin
Odin - personal AI advisor with persistent knowledge brain. Ingests books, articles, videos, documents. Builds principles and positions. Gives referenced advice prioritizing learned knowledge. Nine modes: learn (ingest material), consult (give advice), reflect (review brain), recall (query brain), teach (direct…
knowledge-transfer
Cross-Domain Know-How-Transfer — findet kreative Anwendungen von Vault-Expertise in anderen Branchen.
teach-me
Companion learning skill that makes a codebase legible fast. Surveys a repository, builds a cited map, runs a guided tour in dependency order, and finishes with a validated first change so the learner has actually moved the code. Use when the user runs /teach-me, or asks to learn, understand, onboard onto, get up to…
quiz-me
Companion assessment skill that grills a user on a codebase until their understanding is proven rather than assumed. Asks one question at a time, grades every answer against the real code with citations, scores 0-100 by difficulty tier, and drills the weak areas it finds. Use when the user runs /quiz-me, or asks to be…
explainer-design-system
Turn any codebase into a beautiful, interactive single-page HTML course that teaches how the code works to non-technical people. Use this skill whenever someone wants to create an interactive course, tutorial, or educational walkthrough from a codebase or project. Also trigger when users mention 'turn this into a…