DEDUPED Hot AI repos, turned into use cases Get the Monday 5
137 stars · Python

How to use Deslop GPT: what you can do with it

What is Deslop GPT? deslop is a deletion-first Agent Skill that audits and, when explicitly authorized, removes test bloat, verification theater, and speculative fallbacks from agent-maintained codebases while preserving real behavior.

How do I use it? Open Codex and run $skill-installer with this URL: https://github.com/MrZoyo/deslop-GPT/tree/v0.3.4/skills/deslop; then start Codex in the target repository root; run $deslop deep to request a repository-wide read-only audit. Full steps below.

Trended earlier

View repo on GitHub

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer

What do you want to do?

4 use cases

  • Audit an agent-built repo for removable bloat

    Get a read-only report of test bloat, verification theater, and fallback layers before any edit.

    View prompt
    Using the deslop Skill from MrZoyo/deslop-GPT, run `$deslop deep` as a read-only audit of <target-repo-path>. Expected output: HIGH items with evidence chains and PRESERVE items with reasons. Verify with `git status` that no files were changed.

  • Clean up a branch of agent work before merge

    Trim tests and fallbacks added on the current branch, measured against its merge base.

    View prompt
    Using the deslop Plugin from MrZoyo/deslop-GPT, run `/deslop:deslop current branch apply` on the feature branch in <target-repo-path>. Expected output: a summary of removed tests and fallbacks limited to the branch's merge base. Verify that no staging, commits, or pushes happened without separate permission.

  • Prune duplicate regression tests in a large suite

    Remove self-justifying or overlapping tests while keeping distinct failure coverage.

    View prompt
    Using the deslop Skill from MrZoyo/deslop-GPT, run `$deslop tests apply` on <target-repo-path>. Expected output: a list of removed tests with their coverage rationale. Verify that the remaining test count drops and that the project's own test command still passes.

  • Apply a reviewed repo-wide cleanup

    Carry out the approved removals from a deep audit without redesigning the codebase.

    View prompt
    Using the deslop Skill from MrZoyo/deslop-GPT, run `$deslop deep apply` on <target-repo-path> only for the items approved in the prior audit. Expected output: a change summary tied to approved items. Verify with `git diff --stat` that no unapproved files changed.

Quick start with Deslop GPT

  1. Check you have what it needs: A local git checkout of the target repository; Codex or Claude Code installed; Git, if you install the Skill from a local clone.
  2. Open MrZoyo/deslop-GPT on GitHub and read the README and license.
  3. Open Codex and run $skill-installer with this URL: https://github.com/MrZoyo/deslop-GPT/tree/v0.3.4/skills/deslop
  4. Start Codex in the target repository root.
  5. Run $deslop deep to request a repository-wide read-only audit.
  6. Review the evidence chain behind each HIGH item and each PRESERVE item.

These steps come from our top use case, Audit an agent-built repo for removable bloat, which also has a copy-paste agent prompt.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for MrZoyo/deslop-GPT

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Deslop GPT alternatives · Best AI repos for Software and DevOps

About this repo

  • Who it is forDevelopers and teams whose codebases have grown through repeated coding-agent edit and correction cycles and who want evidence-backed cleanup.
  • Why it is hot137 stars, launched 63 days ago
  • LanguagePython
  • Sourcegithub.com/MrZoyo/deslop-GPT · Back to Hot repos

Requirements

  • A local git checkout of the target repository
  • Codex or Claude Code installed
  • Git, if you install the Skill from a local clone

Add this badge to your README

Maintain Deslop GPT? Show readers where to find these use cases. Use cases on Deduped

Markdown 

[![Use cases on Deduped](https://dedupedai.com/badge/MrZoyo/deslop-GPT.svg)](https://dedupedai.com/use-cases/mrzoyo-deslop-gpt/?utm_source=github&utm_medium=badge&utm_campaign=MrZoyo-deslop-GPT)

HTML 

<a href="https://dedupedai.com/use-cases/mrzoyo-deslop-gpt/?utm_source=github&amp;utm_medium=badge&amp;utm_campaign=MrZoyo-deslop-GPT"><img src="https://dedupedai.com/badge/MrZoyo/deslop-GPT.svg" alt="Use cases on Deduped" height="20"></a>

A static image, no tracking script. About the badge

Questions about Deslop GPT

What is Deslop GPT?

deslop is a deletion-first Agent Skill that audits and, when explicitly authorized, removes test bloat, verification theater, and speculative fallbacks from agent-maintained codebases while preserving real behavior. It is an open-source project on GitHub: https://github.com/MrZoyo/deslop-GPT.

How do I use Deslop GPT?

Open Codex and run $skill-installer with this URL: https://github.com/MrZoyo/deslop-GPT/tree/v0.3.4/skills/deslop; then start Codex in the target repository root; run $deslop deep to request a repository-wide read-only audit. The use cases on this page give the full steps and a copy-paste agent prompt for each job.

Who is Deslop GPT for?

Developers and teams whose codebases have grown through repeated coding-agent edit and correction cycles and who want evidence-backed cleanup.

What can I do with Deslop GPT?

4 use cases so far, for example: Audit an agent-built repo for removable bloat; Clean up a branch of agent work before merge; Prune duplicate regression tests in a large suite. Each has steps and a copy-paste agent prompt.

What do I need to run Deslop GPT?

A local git checkout of the target repository; Codex or Claude Code installed; Git, if you install the Skill from a local clone.

What are alternatives to Deslop GPT?

Other hot AI repos in Software and DevOps: Deep Infer, Harness2, Orca, Opencode, Graphify.

Is Deslop GPT safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.