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 rjmurillo/ai-agents --skill book-to-skillgit clone --depth 1 https://github.com/rjmurillo/ai-agentsWrote 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/rjmurillo/ai-agents/book-to-skill)<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/book-to-skill"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/book-to-skill/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/rjmurillo/ai-agents/book-to-skill"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/book-to-skill.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 | $0.00099 | $0.01777 |
| Opus 5 | $0.00049 | $0.00889 |
| Sonnet 5 | $0.00020 | $0.00355 |
| Haiku 4.5 | $0.00010 | $0.00178 |
Grade A, and why
book-to-skill 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 8d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
book-to-skill
Convert a book's method into the structured input SkillForge needs, then hand off. This skill does NOT generate SKILL.md, score timelessness, triage duplicates, or run activation tests. Those are SkillForge's job.
Triggers
| Trigger phrase | Operation |
|---|---|
turn this book into a skill |
Full workflow: extract method, decide split, hand off to SkillForge |
book-to-skill TITLE |
Same as above, with title named upfront (substitute TITLE) |
extract method from TITLE |
Phase 1 only: produce the structured payload, do not invoke SkillForge |
propose diagnose apply split for TITLE |
Phase 2 only: decide single vs split, no extraction or hand-off |
When to Use
Use this skill when:
- An operator has a book in hand and wants the method captured as one or more skills.
- The book contains a repeatable method (numbered steps, named rules, recurring questions, identified failure modes), not just narrative or argument.
- You want SkillForge's Phase 0-4 gates (triage, timelessness, multi-agent review) to decide whether the skill ships, instead of writing SKILL.md by hand.
Use a different skill when:
- The source is a transcript, voice memo, or unstructured capture. Use
panning-for-gold. - The goal is reference knowledge, not executable procedure. Use
llm-wiki. - You already know exactly what skill you want and need it produced from a goal description rather than a book. Invoke
SkillForgedirectly. - You want to compose existing skills into a slash command. Use
slashcommandcreator.
Out of Scope (do NOT do these)
- Source acquisition. PDFs, ePubs, Kindle decryption, paid summaries. Operator-and-legal problem.
- Producing SKILL.md. SkillForge owns this.
- Triage against existing skills (the 80% duplicate scan). SkillForge's Phase 0 owns this.
- Timelessness scoring. SkillForge's Phase 2.
- Activation tests, paraphrase tests, negative tests. SkillForge's Phase 4 multi-agent panel.
- Fiction, memoir, or pure-narrative books. Halt at Phase 1 pre-condition.
What ships with it
2 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.
- 8d ago First seen · 145 lines · 99 tokens per session scan A d5c6f81724a9
book-to-skill is a skill published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed today), licensed MIT. It adds 99 tokens to every session and 1,777 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
blind-spot-pass
Use before starting work in a domain you don't know well, to surface the "unknown unknowns" — the things you don't even know to ask about — and learn just enough to prompt and decide well. Implements the "blind spot pass" pattern from Anthropic's Fable "finding your unknowns" field guide. Triggers when you say "I'm…
ci-cd
A guide for designing automated build and delivery workflows with GitHub Actions. These workflows can run checks such as tests, code-quality scans, coverage checks, and builds when code is pushed or a pull request is opened.
read-papers
Finds the latest research papers on a specific topic, summarizes their core contributions, and explains complex methodology in plain English.
learning-psychology
Help humans learn through partnership, not instruction.
teach-me
Teach the user a new skill or concept within this workspace. Stateful — the user's learning state persists across sessions and is tracked in workspace files.
deploy
Gated CI/CD pipeline management for GitHub Actions and GitLab CI, plus configuration review for other providers when their authenticated tooling is available. Use to set up or fix CI/CD.