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 nicograef/handbook --skill audiobookgit clone --depth 1 https://github.com/nicograef/handbookWrote 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/nicograef/handbook/audiobook)<a href="https://agentmods.dev/skills/nicograef/handbook/audiobook"><img src="https://agentmods.dev/badge/skills/nicograef/handbook/audiobook/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/nicograef/handbook/audiobook"><img src="https://agentmods.dev/badge/skills/nicograef/handbook/audiobook.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 | $0.00051 | $0.00930 |
| Opus 5.5 | $0.00020 | $0.00372 |
| Sonnet 5.5 | $0.00010 | $0.00186 |
| Haiku 4.5 | $0.00005 | $0.00093 |
Grade A, and why
audiobook 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 18d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audiobook
Subject: $ARGUMENTS. All files live in the output dir, default audiobook/.
Hard rules
- The book is the gap: what the docs assume but never explain. Rewrite from the concept; never restate a doc or tour the repo.
- No length target, and no trimming to hit one. Chapters that shrink each review round mean reviewers compress by habit; revert.
- Every theory claim traces to
sources.mdwith URL and date; nothing from memory. - The checkpoint is the only interaction. Afterwards decide, record it under "Assumptions" in
PLAN.md, and keep going. - ElevenReader narrates everything in the EPUB. Chapters hold no code block, table, diagram, URL or footnote; resolve them into prose.
- The Lua filter only deletes what slipped through; it does not translate.
- Book prose is exempt from the sentence and paragraph caps.
book.epubis a gitignored build artifact; the chapter Markdown is the source. Upload nothing.
Steps
- Scope from the argument and the repo. A whole-repo subject narrows to the subsystem carrying the most concepts.
- Inventory the code and docs on the subject. Name the gaps: missing theory, silent decisions, open questions.
- Checkpoint before research, the first expensive step. Propose defaults for scope (in and out), guiding questions and prior knowledge.
A bare "ja" starts the run. Write the answers to
BRIEF.md. Chapters, order, depth, terms and length are derived, never asked. - Research each open question through the
nico:web-researcheragent. Prior knowledge sets how far back the theory reaches. - Write
PLAN.md: chapters in concept-dependency order, never repo layout, each with its question and prerequisites. Every guiding question is covered. Writeterms.yml(term: NN-slug.md, the chapter that explains it) andmeta.yml(title,creator,lang). - Write the chapters as
NN-slug.mdwith one H1 each. Anchor every concept in a named file or decision. - Review in three rounds, one dimension each. An edit outside its dimension is a defect.
- A, correctness, per chapter: check against the code and
sources.md. An unsourced claim gets a source or goes. - B, structure and terms, once over the book: fix every
${CLAUDE_SKILL_DIR}/check-terms.sh <dir>hit by moving the explanation or the chapter. - C, language and flow, per chapter: no claim, term, order or length changes. Re-check its changed claims against
sources.md; revert breaks to the B wording.
- A, correctness, per chapter: check against the code and
- Render with
${CLAUDE_SKILL_DIR}/md-to-epub.sh --strict <dir> <dir>/book.epub. A finding is a chapter bug: fix the chapter, re-render. - Report the assumptions, every unverified claim, and every drift from
BRIEF.mdwith its reason. Advise a multilingual ElevenReader voice; a German-only one mangles English terms.
What ships with it
3 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.
- 18d ago Changed · +17 lines 7dcb097cce8a
- 23d ago Changed e71f8ec68bbc
- 28d ago Changed 83c363bd2a76
- 1mo ago Changed 7e3b53bd880c
- 1mo ago Changed 92769a32bafe
- 1mo ago Changed f2aeb48a7c71
- 1mo ago Changed 26e254fcc21e
- 1mo ago Changed · -108 lines · -21 tokens per session 5f891466cbbb
- 2mo ago Changed · -3 lines c52bb4d77bf5
- 2mo ago First seen · 145 lines · 72 tokens per session scan A 8863f3b83add
audiobook is a skill published in the GitHub repository nicograef/handbook (2 stars, last pushed 2d ago), licensed MIT. It adds 51 tokens to every session and 930 once invoked, about $0.0002 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 2026-08-31.
audiobook compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| audiobooknicograef/handbook | Skill | 2 | 2d ago | MIT | A | 51 | Claude Code |
| hr-onboardingnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 62 | Claude Code, Codex |
| book-mirrorgarrytan/gbrain | Skill | 32k | yesterday | MIT | A | 138 | Claude Code |
| exam-forecastanthropics/claude-for-legal | Skill | 9.9k | 3d ago | Apache-2.0 | A | 73 | Claude Code |
| lean-formalizewanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | 3d ago | MIT | A | 81 | Claude Code |
| eli5companion-inc/feynman | Skill | 10k | 6d ago | MIT | A | 63 | Claude Code, Codex |
| deck-course-modulenexu-io/html-anything | Skill | 9.4k | 25d ago | Apache-2.0 | A | 25 | Claude Code, Codex |