a-unslop-text

a-unslop-text is a skill for Claude Code, Codex from imisic/claude-marketplace. It costs 232 tokens per session (2,065 once invoked), scanned A, original, MIT.

A prose review and cleanup skill that removes common signs of machine-written text and encourages a deliberate, context-appropriate voice. It focuses on wording and style rather than creating the underlying argument.

In plain words
What is it for?
Use it to edit drafts, remove AI-style wording, apply a house style, and audit prose for mechanical and voice-related problems.
Why use it?
It helps make writing sound less formulaic and removes stock phrases, banned words, unnecessary punctuation, and leftover assistant boilerplate.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: mentions CLAUDE.md.

Part of the unslop plugin — 3 skills shipped together

Good fit Use it to edit drafts, remove AI-style wording, apply a house style, and audit prose for mechanical and voice-related problems.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/imisic/claude-marketplace/a-unslop-text
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 imisic/claude-marketplace --skill a-unslop-text
Clone the repo
git clone --depth 1 https://github.com/imisic/claude-marketplace

Made for: Claude Code, Codex.

Or install unslop, the plugin that ships this one along with the rest of its 3 skills.

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 a-unslop-text

README.md
[![agentmods](https://agentmods.dev/badge/skills/imisic/claude-marketplace/a-unslop-text/github.svg)](https://agentmods.dev/skills/imisic/claude-marketplace/a-unslop-text)
Your own site
<a href="https://agentmods.dev/skills/imisic/claude-marketplace/a-unslop-text"><img src="https://agentmods.dev/badge/skills/imisic/claude-marketplace/a-unslop-text/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 a-unslop-text

Your own site · 80×15
<a href="https://agentmods.dev/skills/imisic/claude-marketplace/a-unslop-text"><img src="https://agentmods.dev/badge/skills/imisic/claude-marketplace/a-unslop-text.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 232 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,065 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 $0.00232 $0.02065
Opus 5 $0.00116 $0.01033
Sonnet 5 $0.00046 $0.00413
Haiku 4.5 $0.00023 $0.00206

Measured 12d ago against content hash 3160e3e49f9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

a-unslop-text 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 12d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/unslop_text_scan.py, tests/test_unslop_text_scan.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/unslop/skills/a-unslop-text/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

a-unslop-text

Read this first, because the common misunderstanding sinks the whole thing.

This skill does not write well for you, and it does not impose a single house voice. It does two narrow things. It removes the specific cues that make text read as machine-written, and where the text reads as AI because nobody chose a voice, it forces a deliberate, register-appropriate one. The argument and what you actually want to say are still yours. A guardrail is not a writer.

Most of the work is the first thing, and most of the first thing is mechanical. The em dash becomes a comma or a period. delve into becomes look at. The sycophantic opener gets cut. The as an AI boilerplate gets deleted. Those are not style calls; there is no voice to invent. Lead with the plain fix. Reserve the deliberate-voice work for the stylistic choices.

How this fits alongside a house style guide

This is the depth layer, not the floor. If you already have an always-on style floor (a house style doc, a project CLAUDE.md rule: no em dash, no bookending, contractions, match length to the question), that floor still applies whether or not this skill loaded. This skill owns the full banned-vocabulary catalog and the scanner, so a single list stays canonical instead of drifting across every project that keeps its own copy.

If you also have a write-time hook that blocks the em dash on public-facing content, that hook and this skill's scanner share the same rule and neither re-derives it: the hook stops it at write time, the scanner catches it at audit time everywhere else.

Per-project overlays sit on top of this layer, not under it: a project's own terminology, provenance rules, and register choice, or a first-person brand voice a project already keeps. Those overlays describe the project; this skill describes the prose.

The trap to avoid

The failure mode of every anti-AI-writing effort is swapping one default register for another. The smooth corporate voice (the em dash, delve, a bulleted list for everything, a tidy "in conclusion") was the 2024 default. The 2026 over-correction is its mirror: staccato three-word fragments, forced lowercase, a here's the thing cold open, a swear bolted on, fake typos to beat a detector. Readers clock the second just as fast. Treat the over-corrected register as its own tell. The fix for a dash is a comma in a sentence you would actually write, not an ellipsis and not a contortion around the gap. See references/writing-with-intent.md.

Read the full file on GitHub · 83 lines

Files

What ships with it

6 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. 12d ago First seen · 83 lines · 232 tokens per session scan A 3160e3e49f9b

Subscribe to this mod's changes

a-unslop-text is a skill published in the GitHub repository imisic/claude-marketplace (2 stars, last pushed 10d ago), licensed MIT. It adds 232 tokens to every session and 2,065 once invoked, about $0.0012 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 2026-08-31.

Related

Other skills, from other repositories

agentic-review

Deep multi-agent code review for local changes. Inspired by AmpCode's agentic review. Use when you want comprehensive analysis of staged changes, unstaged changes, specific commits, or branch differences. Spawns parallel specialized agents (security, performance, patterns, architecture) and synthesizes actionable…

SZoloth/skill-pack · 71 tokens

qa

Full QA on all session changes using Codex as a second pair of eyes. Use when user says "QA", "full QA", "QA my changes", "QA all your changes", or "use codex to review". Runs git diff, sends changes to Codex for thorough review, and synthesizes findings.

SZoloth/skill-pack · 66 tokens

review-responder

Use when receiving feedback on code you implemented, responding to reviewer comments, deciding which review suggestions to implement, or pushing back on incorrect review feedback.

Joncik91/ucai · 33 tokens

pr-sweep

Use when you want to sweep all open pull requests across all repos, triage their status, run code reviews on unreviewed PRs, merge what's ready, fix quick blockers, and produce a full status report. Trigger when the user says "check my PRs", "close out open PRs", "what's the status of my PRs", "sweep my PRs", "PR…

harnessprotocol/harness-kit · 0 tokens

rubber-ducky

Use when you've planned a non-trivial change and are about to implement it, finished a complex or multi-file piece of work, just wrote tests, or are stuck on repeated failures — and any time the user says "rubber duck this", "rubber ducky", "get a second opinion", "sanity-check my plan", "poke holes in this", "what am…

harnessprotocol/harness-kit · 186 tokens

open-pr

Use when wrapping up a development task and getting a PR ready — runs local tests, creates a PR (if one doesn't exist) with a structured description template, conducts a code review via the review skill, and checks CI status with quick fixes. Trigger when the user says they're done with a feature, want to open a PR…

harnessprotocol/harness-kit · 111 tokens