agentmods.dev

de-slopping

de-slopping is a skill for Claude Code from Smirnov-Labs/claude-skills. It costs 66 tokens per session (1,218 once invoked), scanned A, original, MIT.

A final editing pass for written deliverables that removes filler, hedging, long sentences, and unclear wording. It supports a stricter style for documents such as pull requests and runbooks, and a lighter style for explanations and chat.

In plain words
What is it for?
Use it before finishing a pull request or commit message, design document, README, runbook, report, release note, or other prose that needs tightening.
Why use it?
It makes writing easier to scan and reduces the chance that important instructions or decisions are hidden in vague prose. It also checks the draft with a linter before applying broader editorial judgment.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: reads .claude/ paths.

not rated 6repo 2d ago A scan 66 tokens original MIT

Good fit Use it before finishing a pull request or commit message, design document, README, runbook, report, release note, or other prose that needs tightening.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/smirnov-labs/claude-skills/de-slopping
View source ↗ Smirnov-Labs/claude-skills
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 Smirnov-Labs/claude-skills --skill de-slopping
Clone the repo
git clone --depth 1 https://github.com/Smirnov-Labs/claude-skills

Made for: Claude Code.

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 de-slopping

README.md
[![agentmods](https://agentmods.dev/badge/skills/smirnov-labs/claude-skills/de-slopping/github.svg)](https://agentmods.dev/skills/smirnov-labs/claude-skills/de-slopping)
Your own site
<a href="https://agentmods.dev/skills/smirnov-labs/claude-skills/de-slopping"><img src="https://agentmods.dev/badge/skills/smirnov-labs/claude-skills/de-slopping/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 de-slopping

Your own site · 80×15
<a href="https://agentmods.dev/skills/smirnov-labs/claude-skills/de-slopping"><img src="https://agentmods.dev/badge/skills/smirnov-labs/claude-skills/de-slopping.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,218 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 $0.00066 $0.01218
Opus 5.5 $0.00026 $0.00487
Sonnet 5.5 $0.00013 $0.00244
Haiku 4.5 $0.00007 $0.00122

Measured 4d ago against content hash a919f9af2eb0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

de-slopping 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 4d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (hooks/slop_guard.py, hooks/test_slop_guard.py, ste_lint.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.

skills/de-slopping/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

de-slopping

A finishing pass that strips AI-slop from writing before the reader sees it. Inspired by ASD-STE100 Simplified Technical English, the aerospace standard for flight manuals, where one misread sentence can kill someone.

AI prose fails the opposite way. Sentences run long. Claims hedge. Big words do small jobs. Filler sounds like content. This pass removes that. A linter catches the countable slop. I apply the rest by judgment.

When to run it

First classify the text. The mode decides how hard you cut.

  • Strict (every rule): PR and commit messages, design docs, READMEs, runbooks, reports, release notes. Any artifact a reader acts on.
  • Light (cut slop, hedges, em-dashes, and the swap words; keep voice, rhythm, and normal sentence length): chat replies, explanations, teaching.
  • Exempt (do not touch): code, commands, error text, quoted text, file paths, URLs. Those are exact strings.

Full STE strips personality by design. Do not apply strict mode to prose that needs a voice. A de-slop pass with no light mode is a footgun.

The pass

  1. Classify the text as strict, light, or exempt.
  2. Run the linter on the draft: python3 ~/.claude/skills/de-slopping/ste_lint.py <file>, or pipe text on stdin.
  3. Fix every hard finding. Judge each soft finding: keep it or cut it.
  4. Apply the judgment rules below.
  5. Re-run the linter. Confirm zero hard findings.
  6. Send the clean text. Stay quiet about the edit unless asked for an audit.

Rules the linter enforces (mechanical)

The linter counts words and matches patterns. It flags:

  • Sentences over 25 words. Split them into numbered steps.
  • The slop blocklist. Delete on sight: 
    delve  crucial  seamless  comprehensive  robust  cutting-edge
game-changer  tapestry  realm  plethora  myriad  elevate
foster  streamline  meticulous  intricate  pivotal  testament
  • One-word swaps: 
    utilize, leverage        -> use      facilitate      -> help
commence, initiate       -> start    terminate       -> stop
prior to                 -> before   in order to     -> to
additionally, moreover   -> also     approximately   -> about
  • Stock hedges: 
    it's important to note   it's worth mentioning
when it comes to         at the end of the day
  • Every em-dash. Use a comma, a colon, or a period.
  • Soft modals (should, would, may, might): a soft flag. Keep can, will, must. They commit.
  • Filler -ing such as making it easy to: a soft flag.

Read the full file on GitHub · 121 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. 4d ago First seen · 121 lines · 66 tokens per session scan A a919f9af2eb0

Subscribe to this mod's changes

de-slopping is a skill published in the GitHub repository Smirnov-Labs/claude-skills (6 stars, last pushed 2d ago), licensed MIT. It adds 66 tokens to every session and 1,218 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-18.

Writing and docs
Related

Other skills, from other repositories

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens