deslop

deslop is a skill for Claude Code from ivanhoinacki/team-exp-claude-config. It costs 85 tokens per session (975 once invoked), scanned A, original, MIT.

A cleanup workflow for removing unnecessary AI-generated code from the current branch. It targets verbose comments, unused code, needless abstractions, and patterns that do not fit the surrounding code.

In plain words
What is it for?
Use it after implementation and before a commit or pull request to trim noise from changed code without altering unrelated files.
Why use it?
It makes recent changes easier to read and review while protecting intentional code and behavior that was not part of the branch's changes.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

Good fit Use it after implementation and before a commit or pull request to trim noise from changed code without altering unrelated files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ivanhoinacki/team-exp-claude-config/deslop
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 ivanhoinacki/team-exp-claude-config --skill deslop
Clone the repo
git clone --depth 1 https://github.com/ivanhoinacki/team-exp-claude-config

Made for: Claude Code.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/ivanhoinacki/team-exp-claude-config/deslop/github.svg)](https://agentmods.dev/skills/ivanhoinacki/team-exp-claude-config/deslop)
Your own site
<a href="https://agentmods.dev/skills/ivanhoinacki/team-exp-claude-config/deslop"><img src="https://agentmods.dev/badge/skills/ivanhoinacki/team-exp-claude-config/deslop/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 deslop

Your own site · 80×15
<a href="https://agentmods.dev/skills/ivanhoinacki/team-exp-claude-config/deslop"><img src="https://agentmods.dev/badge/skills/ivanhoinacki/team-exp-claude-config/deslop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 975 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 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 5.1 $0.00085 $0.00975
Opus 5 $0.00043 $0.00487
Sonnet 5 $0.00017 $0.00195
Haiku 4.5 $0.00009 $0.00097

Measured 11d ago against content hash 400ebe023bca, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, 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 11d 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/deslop/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Phase 0: Vault RAG (MANDATORY, BEFORE any Read/Grep)

You MUST call query_vault(query, service_filter) BEFORE reading codebase files or external sources. This is enforced by hook. No exceptions.


Remove AI Code Slop

Working Directories

  1. Obsidian workspace (docs, plans, features): __VAULT_ROOT__
  2. Codebase (all LE services): __CODEBASE_ROOT__

Check the diff against main and remove all AI-generated slop introduced in this branch.

Common Agent Mistakes

  1. Over-removing: Deleting code that looks "AI-ish" but was intentionally written. Always check if the pattern exists elsewhere in the file before removing.
  2. Touching unchanged code: Cleaning up code that wasn't part of this branch's diff. Only touch lines that were added/modified in this branch.
  3. Removing useful comments: Not all comments are slop. Domain-specific comments explaining WHY (not WHAT) are valuable. Only remove comments that state the obvious.
  4. Breaking functionality: Removing a defensive check that actually prevents a runtime error. Before removing a try/catch or null check, verify the caller guarantees the value.
  5. Style inconsistency: Making the cleaned code inconsistent with the rest of the file. The goal is to match existing style, not impose "better" style.

Discovery Phase

# Get list of changed files
GIT_EDITOR=true git diff main --name-only

# Get detailed diff to see AI additions
GIT_EDITOR=true git diff main

What to Remove

Slop Patterns (search with Grep tool in changed files)

Use the Grep tool (NOT bash grep) to scan for these patterns in src/:

Unnecessary comments:

  • Grep pattern // This function -> "This function does X" narration comments
  • Grep pattern // TODO: -> TODO comments added by AI (not by user)
  • Grep pattern // eslint-disable -> Disabling lints instead of fixing

Defensive bloat:

  • Grep pattern try \{ -> Unnecessary try/catch wrapping trusted internal calls
  • Grep pattern if.*null|if.*undefined -> Null checks on guaranteed non-null values
  • Grep pattern as any -> Type casts hiding real type issues

Read the full file on GitHub · 103 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. 11d ago First seen · 103 lines · 85 tokens per session scan A 400ebe023bca

Subscribe to this mod's changes

deslop is a skill published in the GitHub repository ivanhoinacki/team-exp-claude-config (2 stars, last pushed 1mo ago), licensed MIT. It adds 85 tokens to every session and 975 once invoked, about $0.0004 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

sdd-tasks

Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.

Gentleman-Programming/gentle-ai · 25 tokens

pr-blocker-summarizer

Summarizes open pull requests into a blockers-first standup digest. Activates when the user asks to summarize open PRs, find blocked pull requests, generate a PR standup, or triage review backlog from a PR export.

FrancyJGLisboa/agent-skill-creator · 54 tokens

review-work

Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.

code-yeongyu/oh-my-openagent · 63 tokens

ijfw-cross-audit

Generate a cross-platform multi-model audit (Trident) on a diff, brief, or artifact. Trigger: 'cross audit', 'Trident', 'second opinion', 'check with other models', 'check with other AIs', 'cross-check this', 'get another perspective', /cross-audit.

FerroxLabs/ijfw · 67 tokens

doc-drift

Use this skill when the user wants to audit the memory and documents Claude Code loads into context — CLAUDE.md (user global + project + nested), MEMORY.md, @imports, .claude/skills, .claude/agents, .claude/commands, installed plugins — and detect four kinds of issues: outdated claims, mutually contradictory…

AlexZio00/sovereign-skills · 240 tokens

ponytail-lazy-senior-dev

Applies the "lazy senior developer" mindset. Use this skill whenever generating, modifying, reviewing code, or fixing bugs to prioritize code reuse, minimalism, YAGNI principles, and root-cause fixes. Also use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni"…

GulajavaMinistudio/awesome-copilot-id · 146 tokens