no-slop

no-slop is a skill for Claude Code from alphabravo-oss/guild. It costs 43 tokens per session (1,114 once invoked), scanned A, original, MIT.

A guide to spotting writing patterns that make documentation, diagrams, and documentation websites feel machine-generated. It includes a script for checking these patterns.

In plain words
What is it for?
It is for checking Markdown prose and diagrams for common quality problems.
Why use it?
It helps remove vague marketing language, repeated phrasing, unsupported numbers, and other distracting habits before publishing.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the webster plugin — 11 skills, 6 agents shipped together

Good fit It is for checking Markdown prose and diagrams for common quality problems.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add alphabravo-oss/guild
Claude Code
/plugin install webster

Made for: Claude Code.

Or install webster, the plugin that ships this one along with the rest of its 11 skills, 6 agents.

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 no-slop

README.md
[![agentmods](https://agentmods.dev/badge/skills/alphabravo-oss/guild/no-slop.svg)](https://agentmods.dev/skills/alphabravo-oss/guild/no-slop)
Your own site
<a href="https://agentmods.dev/skills/alphabravo-oss/guild/no-slop"><img src="https://agentmods.dev/badge/skills/alphabravo-oss/guild/no-slop.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,114 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 $0.00043 $0.01114
Opus 5 $0.00022 $0.00557
Sonnet 5 $0.00009 $0.00223
Haiku 4.5 $0.00004 $0.00111

Measured 3d ago against content hash 6301e1117dc8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

no-slop 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 3d 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.

plugins/webster/skills/no-slop/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

No slop

Copy and residue rules retargeted from rendered HTML to markdown, plus tells specific to documentation and to generated diagrams.

Run the detector rather than eyeballing it:

python3 ${CLAUDE_PLUGIN_ROOT}/scripts/slop.py docs

Exit 1 when anything at high severity fires. Prose rules skip fenced code; diagram rules run only inside mermaid, d2 and dot fences.

Prose

The high severity ones are the ones a reader names out loud.

Tell Why it fails
Marketing buzzwords A superlative that survives a find and replace of the product name is saying nothing about the product
Em dashes The single most named tell in AI prose. Restructure the sentence
"Not just X, but Y" The shape a model falls into when a sentence needs to sound important
"Whether you are a ... or a ..." An audience defined so widely it names nobody
Moreover, Furthermore, In conclusion Connectives marking a connection the sentences do not have
Invented metrics A number with no source is a liability, not just a tell
Hedged claims "Designed to help improve" tells the reader you are not sure it does
Press-release verbs "Serves as", "boasts", "represents" standing in for "is"
Everything in threes One tricolon is a device. By the fourth the reader hears the rhythm instead of the claim

Residue

Worse than slop, because it is a claim the reader cannot check.

  • Agent attribution. A byline naming the tool that wrote it. It says nothing about the content and outlives its accuracy the first time somebody edits underneath it.
  • Conversation artifacts. "Here's the updated function", "I've added error handling". These are replies, written to someone who asked. Committed, they address a reader who was not there.
  • Orchestration markers. A phase or task id. The next reader has no phase and no way to look it up, so the sentence explains the page with a fact they cannot check.
  • Dead scaffold references. A pointer to a plan or handoff file written for one run and deleted after it. The page appears to be explained somewhere and is not.

Read the full file on GitHub · 91 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. 3d ago First seen · 91 lines · 43 tokens per session scan A 6301e1117dc8

Subscribe to this mod's changes

no-slop is a skill published in the GitHub repository alphabravo-oss/guild (2 stars, last pushed 5d ago), licensed MIT. It adds 43 tokens to every session and 1,114 once invoked, about $0.0002 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 2026-09-04.

Related

Other skills, from other repositories

systematic-debugging

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

obra/superpowers · 21 tokens

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

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

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens