dictation-cleanup

dictation-cleanup is a skill for Claude Code, Codex from Ckokoski/AuthorAgent. It costs 21 tokens per session (1,133 once invoked), scanned A, original, MIT.

A writing tool that turns rough speech-to-text dictation into polished prose while keeping the writer’s natural voice.

In plain words
What is it for?
Use it to edit dictated drafts, fix transcription artifacts, organize paragraphs, and prepare spoken first drafts for reading or publishing.
Why use it?
Dictated text often contains filler words, spoken punctuation, repeated thoughts, and awkward sentence breaks that need cleanup before publication.

Skill for Claude CodeCodex

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

Good fit Use it to edit dictated drafts, fix transcription artifacts, organize paragraphs, and prepare spoken first drafts for reading or publishing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ckokoski/authoragent/dictation-cleanup
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 Ckokoski/AuthorAgent --skill dictation-cleanup
Clone the repo
git clone --depth 1 https://github.com/Ckokoski/AuthorAgent

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 dictation-cleanup

README.md
[![agentmods](https://agentmods.dev/badge/skills/ckokoski/authoragent/dictation-cleanup/github.svg)](https://agentmods.dev/skills/ckokoski/authoragent/dictation-cleanup)
Your own site
<a href="https://agentmods.dev/skills/ckokoski/authoragent/dictation-cleanup"><img src="https://agentmods.dev/badge/skills/ckokoski/authoragent/dictation-cleanup/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 dictation-cleanup

Your own site · 80×15
<a href="https://agentmods.dev/skills/ckokoski/authoragent/dictation-cleanup"><img src="https://agentmods.dev/badge/skills/ckokoski/authoragent/dictation-cleanup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,133 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00021 $0.01133
Opus 5 $0.00010 $0.00566
Sonnet 5 $0.00004 $0.00227
Haiku 4.5 $0.00002 $0.00113

Measured 9d ago against content hash 17f6919a29fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

dictation-cleanup 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/_archived/premium/dictation-cleanup/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dictation Cleanup — Premium Skill

Transform messy speech-to-text output into polished, publish-ready prose. Built for authors who dictate their drafts — because dictation is the fastest way to write, but cleaning it up shouldn't take longer than typing it would have.

The Problem

Speech-to-text gives you something like this:

so she walked into the room and um the light was kind of flickering you know
like one of those old fluorescent lights and she could smell something weird
like copper maybe or no more like rust and old pennies and she knew comma she
just knew that something was wrong period new paragraph Marcus was sitting in
the corner but he wasn't really sitting he was more like slumped and his eyes
were open but they weren't seeing anything quote hello question mark close
quote she whispered but even as she said it she knew he wasn't going to answer

What Dictation Cleanup Does

Transforms that into:

She walked into the room. The fluorescent light flickered overhead — one of
those old tubes that never quite dies — and something metallic hung in the air.
Copper. No — rust and old pennies.

She knew. She just knew something was wrong.

Marcus sat in the corner. Slumped, really, more than sitting. His eyes were
open but they weren't seeing anything.

"Hello?" she whispered.

Even as she said it, she knew he wasn't going to answer.

Cleanup Levels

Level 1: Basic (Fastest)

  • Fix punctuation (spoken "comma", "period", "new paragraph")
  • Remove filler words ("um", "uh", "like", "you know", "so")
  • Capitalize and format properly
  • Fix obvious speech-to-text errors
  • Separate paragraphs

Level 2: Standard (Recommended)

Everything in Level 1, plus:

  • Fix run-on sentences (dictation tends to create them)
  • Convert spoken dialogue markers to proper formatting
  • Remove verbal tics and repetitions
  • Smooth out awkward phrasing while keeping author voice
  • Apply Voice Profile for consistency

Level 3: Deep Polish

Everything in Level 2, plus:

  • Restructure rambling passages into tight prose
  • Strengthen verb choices (spoken drafts tend toward weak verbs)
  • Add sensory detail where dictation was vague
  • Balance sentence length variety
  • Scene-level pacing adjustment

Read the full file on GitHub · 143 lines

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 · 143 lines · 21 tokens per session scan A 17f6919a29fe

Subscribe to this mod's changes

dictation-cleanup is a skill published in the GitHub repository Ckokoski/AuthorAgent (105 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 1,133 once invoked, about $0.0001 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.