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 beat-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/beat-writer)<a href="https://agentmods.dev/skills/travsteward/openwriter/beat-writer"><img src="https://agentmods.dev/badge/skills/travsteward/openwriter/beat-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/beat-writer"><img src="https://agentmods.dev/badge/skills/travsteward/openwriter/beat-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 | $0.00281 | $0.01762 |
| Opus 5 | $0.00140 | $0.00881 |
| Sonnet 5 | $0.00056 | $0.00352 |
| Haiku 4.5 | $0.00028 | $0.00176 |
Grade A, and why
beat-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 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Beat Writer
Channel-agnostic, beats-first writer for uncommitted drafts. Owns extraction + shaping; delegates prose to /authors-voice (operator's default anchor — personal voice). Output is a plain OpenWriter doc that can stay generic OR get refactored later into a specific channel via a channel-master writer.
4-layer model:
- EXTRACT — pull beats out of the operator. Same query-first, 5-pass discipline used by
/book-writer. Channel-agnostic CATEGORY tags (CLAIM / REFRAME / MECHANISM / EVIDENCE / STORY / APHORISM / PIVOT / OBJECTION).docs/extraction.md - SHAPE — order beats by reader flow, lock as commitments (no content prescription). No channel template — just a sequenced beats list.
docs/beat-method.md - VOICE —
/authors-voiceApply Protocol with the operator's DEFAULT anchor (personal voice). Same machinery as every other writer; no anchor swap. The piece sounds like the operator. - POLISH —
/polishto 90/100, then/anti-ai, then a naive-reader pass (/congruenceif installed, otherwise inline). Delegated, not duplicated.
Firm rules
-
Single entry point. Invoked as
/beat-writeronly. No subcommands, no flag-syntax args. Internal dispatch from context. -
EXTRACT before WRITE. Same query-first discipline as
/book-writer. AI never invents beats; the operator's head is the source. -
Beats are commitments, not content. Each beat names the OUTCOME (what the reader registers / what shift lands). The voice layer brings the words.
-
No channel template. This skill deliberately does NOT impose a page structure, thread shape, post format, or chapter container. The draft is shapeless-by-design (just a sequenced beat list) so any channel-master can later re-shape it.
-
Voice =
/authors-voiceApply Protocol with operator's DEFAULT anchor. Same machine, default fuel. The piece sounds like the operator. Editor never writes prose directly; every pour is a minion dispatch. Same Rule 1 as/authors-voice.
What ships with it
5 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.
- 9d ago First seen · 119 lines · 281 tokens per session scan A 1cd83b16a6b5
beat-writer is a skill published in the GitHub repository travsteward/openwriter (27 stars, last pushed today), licensed MIT. It adds 281 tokens to every session and 1,762 once invoked, about $0.0014 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…