deslop-code

deslop-code is a skill for Claude Code, Codex from wrannaman/agentic-engineering. It costs 143 tokens per session (1,157 once invoked), scanned A, original, MIT.

A code-cleanup workflow that removes unnecessary lines, duplication, indirection, and unused parts while keeping the code understandable and working.

In plain words
What is it for?
Use it to shorten and simplify code in any language, then run available tests or type checks to catch regressions.
Why use it?
Large or repetitive code is harder to read, review, and maintain, especially when it contains automatically generated clutter.

Skill for Claude CodeCodex

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 skills/wrannaman/agentic-engineering/deslop
Any agent
npx skills add wrannaman/agentic-engineering --skill deslop
Clone the repo
git clone --depth 1 https://github.com/wrannaman/agentic-engineering

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 deslop-code

README.md
[![agentmods](https://agentmods.dev/badge/skills/wrannaman/agentic-engineering/deslop.svg)](https://agentmods.dev/skills/wrannaman/agentic-engineering/deslop)
Your own site
<a href="https://agentmods.dev/skills/wrannaman/agentic-engineering/deslop"><img src="https://agentmods.dev/badge/skills/wrannaman/agentic-engineering/deslop.svg" alt="Measured on agentmods" height="20"></a>
Per session 143 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,157 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 $0.00143 $0.01157
Opus 5 $0.00072 $0.00579
Sonnet 5 $0.00029 $0.00231
Haiku 4.5 $0.00014 $0.00116

Measured 4d ago against content hash 5618c87f7dd1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deslop-code 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 4d 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.

skills/quality/deslop/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.

Aggressively reduce code. Every line must earn its place — strip AI artifacts, remove bloat, and shrink files to their essence while preserving clarity and correctness.

Scope

Default: files changed on the current branch vs main (git diff --name-only main...HEAD). If the user specifies files, directories, or patterns, use those instead.

Process

  1. Get the file list for the scope above
  2. Read each file completely — understand what it does before touching it
  3. Apply reductions file by file, using all applicable techniques below
  4. After all edits, run any available tests/typecheck to confirm nothing broke
  5. Report: files modified, approximate lines removed, notable structural changes

Reduction Techniques

Apply in rough priority order. Each change should pass a simple test: "does the code still read clearly to someone seeing it for the first time?"

Delete dead code

  • Unreachable branches, unused imports, unused variables, unused functions, unused types
  • Feature flags that are always on/off
  • Commented-out code — it's in git history if anyone needs it

Strip AI-generated noise

  • Comments explaining obvious code (// increment counter above count++)
  • Comments more detailed than surrounding file style
  • Section headers/banners (// TYPES ---, // CONSTANTS, // PUBLIC API)
  • Keep only comments explaining WHY, not WHAT
  • Noisy logs: console.log/logger calls with no actionable information (keep errors, warnings, state transitions, external API calls)

Remove defensive bloat

  • try/catch around code that cannot throw
  • Null checks on values already guaranteed non-null by the type system or prior logic
  • Redundant parameter validation inside internal (non-boundary) functions
  • Assertions that duplicate what the type system already enforces
  • Exception: keep defensive code at system boundaries (network calls, file I/O, user input, external APIs)

Collapse indirection

  • Inline functions/methods called exactly once (unless the name provides significant documentation value)
  • Inline single-use variables: const x = foo(); return x;return foo();
  • Flatten unnecessary wrappers: const handleClick = () => doThing() → pass doThing directly
  • Collapse single-implementation interfaces/abstractions — if there's only one implementation and no test mock, the abstraction isn't paying for itself yet

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. 4d ago First seen · 91 lines · 143 tokens per session scan A 5618c87f7dd1

Subscribe to this mod's changes

deslop-code is a skill published in the GitHub repository wrannaman/agentic-engineering (2 stars, last pushed 4mo ago), licensed MIT. It adds 143 tokens to every session and 1,157 once invoked, about $0.0007 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 2026-08-31.

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

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

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens