deslop

Command "deslop" from reliverse/experiments, covering remove ai code slop, remove, keep, do not and heuristic.

Command for Cursor

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.

agentmods
npx agentmods add commands/reliverse/experiments/deslop
Clone the repo
git clone --depth 1 https://github.com/reliverse/experiments

Made for: Cursor.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 250 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00250
Opus 5 $0.00000 $0.00125
Sonnet 5 $0.00000 $0.00050
Haiku 4.5 $0.00000 $0.00025

Measured today against content hash 57533822329d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deslop 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.

.cursor/commands/deslop.md · 39 lines

What it actually says

Remove AI Code Slop

  • Scan the codebase and remove clear artifacts of AI-generated or AI-overassisted code.
  • Act conservatively. Modify only what is unmistakably slop.

Remove

  • Narrative, tutorial, or explanatory comments
  • Comments that restate code behavior
  • Redundant guards, defensive checks, or try/catch in trusted paths
  • Type escapes (any, unsafe forced casts) and unnecessary generics
  • unknown unless strictly required at boundaries
  • Over-engineered patterns without local precedent
  • Naming, structure, or formatting inconsistent with adjacent files

Keep

  • Existing local conventions and implicit assumptions
  • Direct, minimal implementations
  • Working TypeScript inference
  • Unusual or complex code that shows consistent human intent

Do Not

  • Add abstractions, helpers, or layers
  • Introduce new patterns, safety, or best practices
  • Reformat unrelated code
  • Change behavior or semantics

Heuristic

  • If the change does not clearly remove AI slop, do not apply it.
  • When in doubt, leave the code untouched.

Output

  • Finish with a 1–3 sentence summary describing only what was removed.
  • Output nothing else.
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 · 39 lines · 0 tokens per session scan A 57533822329d

Subscribe to this mod's changes

deslop is a command published in the GitHub repository reliverse/experiments (118 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 250 tokens. 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 2026-09-01.