anti-slop

anti-slop is a skill for Claude Code, Codex from alvin-reyes/better-agentic-ide. It costs 47 tokens per session (711 once invoked), scanned A, original, MIT.

Rules against AI slop in code, comments, commit messages and docs. Use whenever you write or edit code, write documentation, a README, a commit message or a PR description, or review changes for quality.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Install with agentmods
npx agentmods add skills/alvin-reyes/better-agentic-ide/anti-slop
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 alvin-reyes/better-agentic-ide --skill anti-slop
Clone the repo
git clone --depth 1 https://github.com/alvin-reyes/better-agentic-ide

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.

agentmods badge for anti-slop

README.md
[![agentmods](https://agentmods.dev/badge/skills/alvin-reyes/better-agentic-ide/anti-slop/github.svg)](https://agentmods.dev/skills/alvin-reyes/better-agentic-ide/anti-slop)
Your own site
<a href="https://agentmods.dev/skills/alvin-reyes/better-agentic-ide/anti-slop"><img src="https://agentmods.dev/badge/skills/alvin-reyes/better-agentic-ide/anti-slop/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 anti-slop

Your own site · 80×15
<a href="https://agentmods.dev/skills/alvin-reyes/better-agentic-ide/anti-slop"><img src="https://agentmods.dev/badge/skills/alvin-reyes/better-agentic-ide/anti-slop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 711 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 unknown 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 $0.00047 $0.00711
Opus 5.5 $0.00019 $0.00284
Sonnet 5.5 $0.00009 $0.00142
Haiku 4.5 $0.00005 $0.00071

Measured today against content hash 5f327c3b94b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

anti-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 today.

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.

claude-plugin/plugins/ade/skills/anti-slop/SKILL.md · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Anti-slop

Slop is output that looks finished but isn't, or that pads the work with words and code nobody asked for. Hold every change to these rules.

Code

  • Do what was asked, and only that. No extra features, options, config flags, abstraction layers or "future-proofing" the task doesn't need.
  • No stubs. Never leave TODO, FIXME, pass, throw new Error("not implemented"), "implement this", "your logic here" or "... rest of the code". Write the real code, or say plainly what you didn't do and why.
  • No debug leftovers. Remove console.log, print debugging and debugger statements you added. Real logging goes through the project's logger.
  • No commented-out code. Delete it; git keeps history.
  • Comments explain why, not what. Don't narrate code ("This function adds two numbers", "Increment i"). Keep comments that record a reason, a constraint or a non-obvious decision.
  • Match the codebase. Follow the file's naming, structure, error handling and comment density. Reuse existing helpers instead of writing near-duplicates.
  • No new files without a reason. Don't add READMEs, example files, summary markdown or test scaffolding unless asked.
  • Don't swallow errors. No empty catch, no except: pass, no silent fallbacks that hide a failure.
  • Tests test behaviour. No tests that only assert a mock was called, no snapshot dumps nobody reads, no tests edited to pass without fixing the cause.
  • Finish the loop. Run the project's typecheck, lint and tests for what you touched. Report failures honestly.

Writing (docs, READMEs, commit messages, PR descriptions, replies)

  • Lead with the point. First sentence says what changed or what the answer is.
  • Plain words. Not: delve, leverage, utilize, robust, seamless, cutting-edge, game-changer, supercharge, elevate, unlock, embark, tapestry, "in today's fast-paced world", "it's worth noting", "a testament to".
  • No filler. Cut openers ("Great question!", "Certainly!"), recaps of what the reader just read, and closing offers of more help.
  • No hype or hedging stacks. Say what it does. Qualify only when it matters.
  • Formatting serves the reader. No emoji in headings, no bold on every other phrase, no bullet lists for things that read better as a sentence.
  • Commit messages: imperative subject under ~70 characters, then what and why. No "This commit...".
  • Be specific. Name the file, the function, the number. "Improved performance" says nothing; "cut cold start from 2.1 s to 0.8 s" does.

Read the full file on GitHub · 36 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. today First seen · 36 lines · 47 tokens per session scan A 5f327c3b94b3

Subscribe to this mod's changes

anti-slop is a skill published in the GitHub repository alvin-reyes/better-agentic-ide (85 stars, last pushed 9d ago), licensed MIT. It adds 47 tokens to every session and 711 once invoked, about $0.0002 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 2026-10-26.