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 smk-labs/claude-plugins --skill new-bookgit clone --depth 1 https://github.com/smk-labs/claude-pluginsWrote 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/smk-labs/claude-plugins/new-book)<a href="https://agentmods.dev/skills/smk-labs/claude-plugins/new-book"><img src="https://agentmods.dev/badge/skills/smk-labs/claude-plugins/new-book/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/smk-labs/claude-plugins/new-book"><img src="https://agentmods.dev/badge/skills/smk-labs/claude-plugins/new-book.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 | $0.00000 | $0.01375 |
| Opus 5 | $0.00000 | $0.00687 |
| Sonnet 5 | $0.00000 | $0.00275 |
| Haiku 4.5 | $0.00000 | $0.00137 |
Grade A, and why
new-book 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 9d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
new-book: turn the plan into lessons
The plan says what to teach. This skill writes it, in the exact shape a future session can pick up and deliver without thinking.
Read reference/teaching-rules.md and reference/file-formats.md first. Every authoring agent gets the rules verbatim, because a lesson that breaks them is worse than no lesson.
Step 1: find the next book
Read STATE.md, TOC.md, PROFILE.md, and .course/synthesis.json. The next book is the first one in TOC.md whose chapter files do not exist under books/.
If .course/ is missing, say so plainly and offer to rebuild the plan from TOC.md and TAXONOMY.md. Those two files carry enough to reconstruct briefs, though the teaching angles from the original research will be lost.
If the learner asked for a specific book out of order, check its prerequisites in TOC.md first and tell them what they will be missing. Then do what they asked.
Step 1b: illustrated or not
Read .course/config.json. If illustrations is on for this book or for the whole course, every lesson gets one image that carries the mechanism: a diagram, a photograph of the real thing, a chart. Never a decoration. Fetch them with /getpix:getpix after the chapters are written, and reference the saved file from the lesson.
If the setting is missing and the subject is visual, anatomy, design, geography, hardware, anything where the thing itself must be seen, offer it once in a single question and record the answer in the config. Otherwise leave it off and do not ask again.
Check that the installed readable version can display an image inside a card before you promise illustrated lessons. If it cannot, say so plainly and write the book without images rather than producing lessons that reference files nothing will render.
Step 2: research only where it is needed
TOC.md marks the chapters that need a fresh look, usually because the material moves fast or is tooling-specific. For only those, run one short research agent each: two or three searches, no page fetching, output a brief list of what changed and what current guidance says, written to .course/briefs/<CHAPTER-ID>-research.md.
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.
- 9d ago First seen · 79 lines · 0 tokens per session scan A 30c9d3c0561b
new-book is a skill published in the GitHub repository smk-labs/claude-plugins (11 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,375 tokens. 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 skills, from other repositories
learn
Personalized tutor with memory across sessions — "teach me X, at my pace." Builds a syllabus with a pass rubric per unit, teaches one unit per session: a recall quiz on what's due (date-based spaced repetition), examples matched to your background, and an active-recall check graded against the rubric with confidence…
meta-learn
Deliberate deep-dive capture for a completed skill session that deserves more than the automatic one-line row every T1/T2 skill already logs at its own close — asks three extraction questions (what surprised you, what was wrong, what was missing), turns real answers into specific, falsifiable pattern statements, and…
explain
Comprehensive deep-dive explanation of GitHub repos, live websites/products, competitors, data products, algorithms/calculators, concepts, or any topic. Spawns parallel research + exploration agents, drives a real browser for live products, reverse-engineers calculators to runnable validated code, and saves a full doc…
becoming-senior-pm
Use this skill when the user asks "how do I become a senior PM", "what does senior PM actually mean", "I want to get promoted to senior", "what's the difference between PM and senior PM", "I've been a PM for 2–3 years and want to grow", "my manager says I need to work more strategically", "I'm stuck at PM level", or…
solo-to-cpo
Use this skill when the user asks about "career path to CPO", "how do I become a CPO", "PM career progression", "path from PM to VP Product", "PM career growth", "how do I grow as a PM", "what does the PM career ladder look like", "solo PM to product leader", or wants to understand and plan their PM career trajectory…
technical-pm
Use this skill when the user asks about "working with engineers as a PM", "how technical should a PM be", "I feel out of my depth with engineers", "how to earn engineering trust", "how to read code as a PM", "should I learn to code", "bridging the gap with engineering", "technical credibility for PMs", or wants to…