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 travsteward/openwriter --skill book-writergit clone --depth 1 https://github.com/travsteward/openwriterWrote 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/travsteward/openwriter/book-writer)<a href="https://agentmods.dev/skills/travsteward/openwriter/book-writer"><img src="https://agentmods.dev/badge/skills/travsteward/openwriter/book-writer/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/travsteward/openwriter/book-writer"><img src="https://agentmods.dev/badge/skills/travsteward/openwriter/book-writer.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 | $0.00230 | $0.03435 |
| Opus 5 | $0.00115 | $0.01717 |
| Sonnet 5 | $0.00046 | $0.00687 |
| Haiku 4.5 | $0.00023 | $0.00344 |
Grade A, and why
book-writer 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 10d 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Book Writer
Book-scale orchestration skill. Pairs with /authors-voice (voice pipeline). Together: this skill specifies WHAT must land in each beat; /authors-voice specifies HOW the prose sounds.
FIRM RULES
0. Author owns substance. The agent QUERIES — it does not propose from cold.
The load-bearing rule. It governs every book-start, not just beat work, and it is stated here (not only in docs/beats.md) so it is in context the moment any book begins. Author owns substance + beat material; the agent owns process + shape.
On ANY book-start intent — "write a book", "start writing it", "start a book project", "draft a chapter" — the substance comes OUT of the author before any beats or prose exist. The default is to QUERY, never to manufacture:
- Every book (and every chapter) begins with the author DUMP (
docs/beats.md→ 5-pass, Pass 1): the author brain-dumps the material; the agent captures it verbatim, then structures it. No beats, no chapter shape, and no prose exist before the author has dumped. - Never propose beats from cold — mined from the premise, source docs, or the agent's own intuition. The documented failure mode: the author rejects them because they came from outside the author's brain. Pull the material out of the author with focused questions; structure what comes back.
- The agent proposes only in the narrow documented cases (
docs/beats.md→ "When proposing IS the right move"): the author explicitly asks for candidates, the agent is mechanically restructuring source the author already owns, or the author has said move fast on low-stakes draft work. Anything the agent originates this way is shown to the author as a proposal — the agent never calls its own output "locked."
If you reach for beats or prose and the author has not dumped the material, you have skipped step one. STOP and run the dump.
Full method: docs/beats.md (Query-first principle + the 5-pass extraction). Fiction runs the scene-shaped fork of the same 5-pass — docs/beats-fiction.md.
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.
- 10d ago First seen · 195 lines · 230 tokens per session scan A cbf1192cb887
book-writer is a skill published in the GitHub repository travsteward/openwriter (27 stars, last pushed yesterday), licensed MIT. It adds 230 tokens to every session and 3,435 once invoked, about $0.0011 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 2026-08-30.
Other skills, from other repositories
anti-ai-writing
Use when writing or editing any prose for a human reader - documentation, READMEs, emails, reports, captions, scripts, blog posts, UI copy, commit messages, PR descriptions - or when asked to remove AI tells, de-slop text, make writing sound human, or check writing style. Applies 29 researched patterns that make text…
humanize-pro
Use when the user asks to humanize, unslop, de-slop, de-AI, clean up, tighten, or make text sound human or natural; when they say something reads like AI or like ChatGPT; when they ask whether something matches their voice or style guide; or when drafting or rewriting outbound human communication: LinkedIn, X, cold or…
anti-slop
Remove AI slop from any voice-bearing prose — original posts, threads, articles, long-form, emails, docs, READMEs, marketing copy, bios, scripts. Use when drafting text meant to sound like a specific person or brand, when rewriting text that reads generic, corporate, or AI-generated, or when asked to humanize…
humanizer-workbench
Rewrites AI-generated text into natural, human-quality writing using a multi-stage detection and transformation pipeline.
writing-humanizer
A text-editing skill that removes patterns often associated with AI-written prose and makes writing sound more natural. Its instructions are aimed mainly at Traditional Chinese text used in Taiwan.
kill-slop
Audit a file or draft for AI slop and off-voice lines against the author's bound voice, report findings with in-voice swaps, then apply approved fixes. Use when the user says "kill slop", "/kill-slop [file]", "find the slop in this", "audit this for slop", or wants a deck, article, page, or draft cleaned to sound like…