A writing review and rewriting workflow that removes formulaic AI wording while preserving the original meaning, clarity, and tone.

Editing documentation, emails, posts, reports, and other text, or flagging AI-writing patterns without rewriting when an audit is requested.

It helps prose sound more natural and direct instead of repetitive or machine-written.

stop-slop — Skill for Claude Code and Codex by odinfree

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 odinfree/stop-slop-refined --skill stop-slop-refined

Clone the repo

git clone --depth 1 https://github.com/odinfree/stop-slop-refined

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/odinfree/stop-slop-refined/stop-slop-refined/github.svg)](https://agentmods.dev/skills/odinfree/stop-slop-refined/stop-slop-refined)

Your own site

<a href="https://agentmods.dev/skills/odinfree/stop-slop-refined/stop-slop-refined"><img src="https://agentmods.dev/badge/skills/odinfree/stop-slop-refined/stop-slop-refined/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/odinfree/stop-slop-refined/stop-slop-refined"><img src="https://agentmods.dev/badge/skills/odinfree/stop-slop-refined/stop-slop-refined.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,441 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00102	$0.03441
Opus 5.5	$0.00041	$0.01376
Sonnet 5.5	$0.00020	$0.00688
Haiku 4.5	$0.00010	$0.00344

Measured 1mo ago against content hash e22f2f625d44, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

stop-slop scanned grade A with 1 finding 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 1mo ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/build_revision_artifact.mjs, scripts/generate-site-data.mjs), 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Flag clusters of tells, not isolated ones. A single em dash, one transition word, or perfect grammar alone means nothing. Mixed registers, salutations, and curly quotes alone (editors auto-curl them) are not AI evidence.

SKILL.md · 233 lines

How it starts

The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stop Slop

Audit and rewrite prose to remove formulaic AI writing while preserving meaning, clarity, source boundaries, and useful voice.

This file is the package router and default operating guide.

Companion files:

Modes

rewrite (default) — Diagnose the full draft internally, rewrite it, then run a second reader pass. Return the clean prose first. Show issues, scores, or a diff when the user asks or when the changes need review.

detect — Flag only. No rewriting. Use when the patterns might be intentional, when auditing someone else's writing, or when the writer wants to fix things themselves.

Trigger detect when the user says "detect," "flag," "scan," "audit," "audit only," or "what's wrong with this." Default to rewrite otherwise.

Default baseline

Use plain writing for neutral notes, summaries, reports, documentation, research, and ordinary email.

Use common words.
Write complete sentences and keep closely related clauses together.
Explain the literal mechanism before adding style.
Keep a necessary technical term and explain it once.
Repeat the correct noun when changing it would make the subject harder to track.
Remove filler and decorative formatting.

An intentional fragment may stay when the source voice or format earns it. An analogy may stay when it makes an unfamiliar idea easier to understand after the literal explanation is clear. Apply a separate personal-voice overlay only when the user asks for it or the artifact already carries it.

Domain term collisions

In Starknet, ZK, cryptography, and post-quantum writing, do not use receipt, proof, or proof point as generic strategy words.

receipt reads like AI lingo and most readers do not know what it means.
proof has a literal meaning in this domain. Use it only for mathematical, cryptographic, legal, or source-quoted proof.
evidence is allowed. It is often the plain word when the sentence means support for a claim.

Read the full file on GitHub · 233 lines

Files

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.

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.

1mo ago Changed e22f2f625d44
2mo ago First seen · 233 lines · 102 tokens per session scan A ac936317f253

Subscribe to this mod's changes

stop-slop is a skill published in the GitHub repository odinfree/stop-slop-refined (13 stars, last pushed 1mo ago), licensed MIT. It adds 102 tokens to every session and 3,441 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Writing and docs

stop-slop next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
stop-slopodinfree/stop-slop-refined	Skill	13	1mo ago	MIT	A	102	Claude Code, Codex
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code

stop-slop