Skip to content
SkillModel-led1,980 tokens in use

Antislop Code

Removes generic AI-style comments from code, keeps the ones that carry real information, and never touches the code itself.

9,688 stars on the repository MIT Licensemiqdadbadjuber/anti-slop · skills/antislop-code
npx skills add miqdadbadjuber/anti-slop
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing Antislop Code costs

29tokens idle
1,980tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

writes filesdeclared

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter8/15
  • Structure17/25
  • Examples9/15
  • Output15/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity100
  • Maintenance100
  • Community52
  • Maturity20
  • Momentum40

Antislop Code is the code comment skill of the antislop rulebook. When a task writes or edits comments, it filters out the ones that read as machine-made: banner separators, comments that restate the next line, step-by-step narration, empty labels, vague TODOs, signature echoes, decorative emoji and end markers.

It keeps comments that explain intent, security, performance, workarounds and edge cases, and it limits itself to comments only.

What You Get

  • A catalog of useless comment patterns with a fix for each
  • A list of comment kinds that must stay, such as business logic, security, concurrency and workarounds
  • A length rule: one line, or two only when the second adds a new fact
  • A comment checklist to run alongside the core Delivery Gate
  • A guarantee that only comments change

Common Use Cases

  • Cleaning a file full of AI-written banner and narration comments
  • Keeping generated code comments short while it is being written
  • Reviewing a pull request for comments that repeat the code
  • Replacing vague TODOs with specific tasks or removing them

What Makes It Unique

Many linters flag comment style. This skill judges whether a comment carries a fact the code does not show, and it protects the valuable ones with an explicit keep list. It also targets over-long comments, where the length itself is the tell, and cuts them to the one constraint that matters.

Under The Hood

The skill is a single SKILL.md of instructions with no scripts. The frontmatter allows the agent to read, write and edit files and to search with glob and grep. When you apply it, the agent opens your source files, removes or shortens comments and saves the edits. It does not run commands, fetch web pages or call APIs. It is meant to load together with the core antislop skill, whose rules it cites by number.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers