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.
npx agentmods add instructions/gabelul/slopbuster/claude-mdgit clone --depth 1 https://github.com/gabelul/slopbusterWrote 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.
[](https://agentmods.dev/instructions/gabelul/slopbuster/claude-md)<a href="https://agentmods.dev/instructions/gabelul/slopbuster/claude-md"><img src="https://agentmods.dev/badge/instructions/gabelul/slopbuster/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00779 | $0.00779 |
| Opus 5 | $0.00390 | $0.00390 |
| Sonnet 5 | $0.00156 | $0.00156 |
| Haiku 4.5 | $0.00078 | $0.00078 |
Grade A, and why
slopbuster CLAUDE.md 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — slopbuster
What this is
A skill (pure markdown, no runtime) that strips AI-generated patterns from text, code, and academic writing. Works with Claude Code, Codex CLI, Cursor, and 40+ other coding agents via the Skills CLI.
Architecture
SKILL.md is the orchestrator. It routes between three modes (text, code, academic), defines the two-pass audit process, and references sub-files for the actual rules.
SKILL.md — entry point, mode routing, output format, process flow
SKILL-OC.md — token-optimized version (same content, compressed for OpenClaw)
rules/text-*.md — 5 files covering 24 prose patterns
rules/code-*.md — 6 files covering 79 code patterns
rules/academic.md — 49 rules across 10 groups with section-specific guidance
guides/voice-and-soul.md — how to inject personality (not just strip patterns)
guides/style-template.md — template for building custom voice profiles
scoring.md — three-tier weighted scoring system
Rule files are loaded selectively based on mode. Text mode loads text-*.md, code mode loads code-*.md, academic loads academic.md. The guides and scoring are shared across modes.
How the skill works
- Diagnose — load relevant rule files, scan for matching patterns, score original
- Rewrite — apply pattern removals, inject human voice markers
- Two-pass audit — ask "what's still AI about this?", list remaining tells, revise again
- Report — score final version, generate changelog, flag manual review items
The two-pass audit is the differentiator. First pass removes patterns. Second pass catches the sterile, voiceless text that pattern removal itself creates.
Scoring system
Three tiers, weighted by signal strength:
- Tier 1 (3pts): dead giveaways — delve, tapestry, sycophancy, chatbot artifacts
- Tier 2 (2pts): corporate tells — synergy, leverage, copula avoidance, significance inflation
- Tier 3 (1pt): weak signals — Additionally, Furthermore, em dashes, mild hedging
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.
- 5d ago First seen · 82 lines · 779 tokens per session scan A 7f50ba558662
slopbuster CLAUDE.md is an instructions file published in the GitHub repository gabelul/slopbuster (38 stars, last pushed 1mo ago), licensed MIT. It adds 779 tokens to every session, about $0.0039 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.
Other instructions, from other repositories
logic-lens CLAUDE.md
Instructions for hyhmrright/logic-lens, covering logic-lens — developer guide (claude code), project layout, conventions, skill.md structure and guide files.
logic-lens AGENTS.md
Instructions for hyhmrright/logic-lens, covering logic-lens — developer guide (codex cli), invoking skills, project layout, key conventions and no hooks.
logic-lens GEMINI.md
Instructions for hyhmrright/logic-lens, covering logic-lens — developer guide (gemini cli), invoking skills, installation, project layout and key conventions.
agentic-hardening-skill AGENTS.md
Instructions for Calvin-LLC/agentic-hardening-skill, covering harden and rules.
shuorenhua-zh-tw AGENTS.md
Instructions for tentenco/shuorenhua-zh-tw, covering 倉庫說明, 語言, 風格, 布局 and 協作.
shuorenhua-zh-tw CLAUDE.md
Instructions for tentenco/shuorenhua-zh-tw, a project described as: 繁體中文（臺灣）AI 味清理 Skill：去 AI 腔、清中港用語、修簡轉繁錯字、教育部標點、七種出版語體。AI humanizer skill for Traditional Chinese (Taiwan) — Claude Code / Codex / Cursor / ChatGPT.