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 | $0.00063 | $0.01295 |
| Opus 5.5 | $0.00025 | $0.00518 |
| Sonnet 5.5 | $0.00013 | $0.00259 |
| Haiku 4.5 | $0.00006 | $0.00129 |
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 1mo 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 — 82 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.
- 1mo ago Changed · +3 lines · +63 tokens per session bdb7d7cd2148
- 1mo 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 28d ago), licensed MIT. It adds 63 tokens to every session and 1,295 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
meta-learn
Captures a completed skill session in depth: three extraction questions (what surprised you, what was wrong, what was missing) become falsifiable pattern statements, logged to /context/skill-sessions.md for meta-synthesis. Trigger on: "capture what we learned", "log this session", "save the learnings", "what did we…
pmm-resume
Reviews and tailors a PMM resume (IC to VP, including AI PMM roles): dissects the job description, ranks bullets by impact fit and rebuilds the complete resume in one pass. Trigger on: resume + JD paste, "tailor this", "which bullets for this role", "rebuild for [company]", "review my PMM resume", "reframe for…
product-marketing-context
Builds and maintains the shared GTM brain (product context, ICP, positioning, voice, market context, proof points, plus optional strategy and execution sections and the deal-reality fields) that every other skill reads before producing output. Works standalone from your own answers, and gets stronger when you connect…
competitor-deep-dive
Builds a long-form, fully sourced deep-dive on one competitor for a named decision (strategy call, RFP, pricing change, roadmap bet), with dated reviews, deal evidence, a head-to-head per offering and where they win. Triggers: "deep-dive on [competitor]", "full competitor write-up", "what do users really say about…
workflow-orchestrator
Chains positioning, competitive, GTM strategy, campaign briefs, stakeholder maps and retros into one coherent PMM program with a master document and brain updates. Trigger on: "run full GTM workflow", "run a full launch", "launch [product] end to end", "positioning refresh", "quarterly PMM cycle", "competitive…
positioning-messaging
Builds or audits positioning statements, messaging hierarchies, homepage copy and persona cards using April Dunford's Obviously Awesome framework, in five modes (build, audit, fletch, sales-enablement, homepage). Refuses to generate without a named primary persona and 3+ alternatives including status quo, and blocks…