beat-writer

beat-writer is a skill for Claude Code, Codex from travsteward/openwriter. It costs 281 tokens per session (1,762 once invoked), scanned A, original, MIT.

A workflow for shaping an uncommitted piece of writing before deciding whether it will become a blog post, social-media thread, newsletter section, or another format. It extracts ideas, orders them into beats, and prepares a draft for prose writing.

In plain words
What is it for?
Use it to turn a brain dump into a sequence of claims, evidence, stories, objections, and other writing units, then prepare the piece for polishing and editing.
Why use it?
It gives scattered ideas a clear structure while keeping the final publishing format open.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to turn a brain dump into a sequence of claims, evidence, stories, objections, and other writing units, then prepare the piece for polishing and editing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/travsteward/openwriter/beat-writer
Install

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.

Any agent
npx skills add travsteward/openwriter --skill beat-writer
Clone the repo
git clone --depth 1 https://github.com/travsteward/openwriter

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for beat-writer

README.md
[![agentmods](https://agentmods.dev/badge/skills/travsteward/openwriter/beat-writer/github.svg)](https://agentmods.dev/skills/travsteward/openwriter/beat-writer)
Your own site
<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.

agentmods 80×15 button for beat-writer

Your own site · 80×15
<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>
Per session 281 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,762 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 9d ago against content hash 1cd83b16a6b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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.

skills/beat-writer/SKILL.md · 119 lines

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:

  1. 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
  2. SHAPE — order beats by reader flow, lock as commitments (no content prescription). No channel template — just a sequenced beats list. docs/beat-method.md
  3. VOICE/authors-voice Apply Protocol with the operator's DEFAULT anchor (personal voice). Same machinery as every other writer; no anchor swap. The piece sounds like the operator.
  4. POLISH/polish to 90/100, then /anti-ai, then a naive-reader pass (/congruence if installed, otherwise inline). Delegated, not duplicated.

Firm rules

  1. Single entry point. Invoked as /beat-writer only. No subcommands, no flag-syntax args. Internal dispatch from context.

  2. EXTRACT before WRITE. Same query-first discipline as /book-writer. AI never invents beats; the operator's head is the source.

  3. Beats are commitments, not content. Each beat names the OUTCOME (what the reader registers / what shift lands). The voice layer brings the words.

  4. 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.

  5. Voice = /authors-voice Apply 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.

Read the full file on GitHub · 119 lines

Files

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.

Changes

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.

  1. 9d ago First seen · 119 lines · 281 tokens per session scan A 1cd83b16a6b5

Subscribe to this mod's changes

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.

Related

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…

Abdulkader-Safi/AI-Writing-Rules · 78 tokens

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…

msdanyg/humanize-pro · 168 tokens

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…

aixarizzo/kill-slop · 138 tokens

humanizer-workbench

Rewrites AI-generated text into natural, human-quality writing using a multi-stage detection and transformation pipeline.

aprempeh-tech/humanizer-workbench · 0 tokens

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.

shyuan/writing-humanizer · 92 tokens

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…

aixarizzo/kill-slop · 119 tokens