# AI use cases for Deslop GPT (MrZoyo/deslop-GPT) Repo: [MrZoyo/deslop-GPT](https://github.com/MrZoyo/deslop-GPT) | Use cases: 4 | Page: https://dedupedai.com/use-cases/mrzoyo-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. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Audit an agent-built repo for removable bloat: https://dedupedai.com/use-cases/mrzoyo-deslop-gpt/audit-agent-built-repo-deep/ - Clean up a branch of agent work before merge: https://dedupedai.com/use-cases/mrzoyo-deslop-gpt/clean-current-branch-before-merge/ - Prune duplicate regression tests in a large suite: https://dedupedai.com/use-cases/mrzoyo-deslop-gpt/prune-duplicate-regression-tests/ - Apply a reviewed repo-wide cleanup: https://dedupedai.com/use-cases/mrzoyo-deslop-gpt/apply-reviewed-repo-wide-cleanup/ ## How to audit an agent-built repo for removable bloat with Deslop GPT Repo: [MrZoyo/deslop-GPT](https://github.com/MrZoyo/deslop-GPT) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README Get a read-only report of test bloat, verification theater, and fallback layers before any edit. **Who it is for:** A developer whose repo has grown through many agent edit and fix cycles and who wants to see what could be cut before changing anything. **The problem:** Redundant tests, producer-verifies-producer checks, and fallback layers pile up, and it is hard to tell which ones still protect real behavior. **The outcome:** A repository-wide list of high-confidence removals with evidence chains, plus a list of behavior the Skill chose to preserve, with no files changed. ### Steps 1. Open Codex and run `$skill-installer` with this URL: https://github.com/MrZoyo/deslop-GPT/tree/v0.3.4/skills/deslop 2. Start Codex in the target repository root. 3. Run `$deslop deep` to request a repository-wide read-only audit. 4. Review the evidence chain behind each HIGH item and each PRESERVE item. 5. Do not run `apply` yet. Keep the report for review. ### Prompt to paste into your agent ```text Using the deslop Skill from MrZoyo/deslop-GPT, run `$deslop deep` as a read-only audit of . Expected output: HIGH items with evidence chains and PRESERVE items with reasons. Verify with `git status` that no files were changed. ``` ### Caveat The README says the Skill favors keeping code when evidence is incomplete, so the audit may list fewer removals than you expect. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/mrzoyo-deslop-gpt/audit-agent-built-repo-deep/ ## How to clean up a branch of agent work before merge with Deslop GPT Repo: [MrZoyo/deslop-GPT](https://github.com/MrZoyo/deslop-GPT) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Trim tests and fallbacks added on the current branch, measured against its merge base. **Who it is for:** A developer about to merge a feature branch that was built mostly by a coding agent and wants the extra machinery removed first. **The problem:** Agent work on a branch often adds overlapping tests and defensive layers that make the merge harder to review. **The outcome:** Scoped cleanup limited to what the branch added relative to its merge base, ready for the developer to review and commit. ### Steps 1. In Claude Code, run `/plugin marketplace add MrZoyo/deslop-GPT`. 2. Run `/plugin install deslop@deslop`. 3. Check out the feature branch in the target repository. 4. Run `/deslop:deslop current branch apply` and review every change it makes. (inferred, check the README) 5. Run the project's own test suite before committing the cleanup. (inferred, check the README) ### Prompt to paste into your agent ```text Using the deslop Plugin from MrZoyo/deslop-GPT, run `/deslop:deslop current branch apply` on the feature branch in . 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. ``` ### Caveat Only apply authorizes edits, and staging, commits, pushes, and branch changes still need separate permission, so you must commit the result yourself. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/mrzoyo-deslop-gpt/clean-current-branch-before-merge/ ## How to prune duplicate regression tests in a large suite with Deslop GPT Repo: [MrZoyo/deslop-GPT](https://github.com/MrZoyo/deslop-GPT) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Remove self-justifying or overlapping tests while keeping distinct failure coverage. **Who it is for:** A maintainer whose test suite has grown with overlapping agent-written tests and who wants a faster, clearer suite. **The problem:** Many tests check the same thing, and some only verify code that was written to satisfy them. **The outcome:** A reduced test set in which each remaining test protects a distinct success, rejection, error, or edge-case behavior. ### Steps 1. Install the Skill in Codex with `$skill-installer` using https://github.com/MrZoyo/deslop-GPT/tree/v0.3.4/skills/deslop 2. Open the target repository in Codex. 3. Run `$deslop tests apply` to prioritize test signal and mutual-support test and code clusters. (inferred, check the README) 4. Review each deleted test and confirm its behavior is covered elsewhere. 5. Run the project's own test suite and confirm it still passes. (inferred, check the README) ### Prompt to paste into your agent ```text Using the deslop Skill from MrZoyo/deslop-GPT, run `$deslop tests apply` on . 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. ``` ### Caveat The README says the Skill reduces test surface, not behavior surface, so a smaller suite is only good if the remaining tests still guard the same behavior. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/mrzoyo-deslop-gpt/prune-duplicate-regression-tests/ ## How to apply a reviewed repo-wide cleanup with Deslop GPT Repo: [MrZoyo/deslop-GPT](https://github.com/MrZoyo/deslop-GPT) | Difficulty: Advanced | Time: 60 minutes | Basis: From the README Carry out the approved removals from a deep audit without redesigning the codebase. **Who it is for:** A tech lead who has already reviewed a deep audit report and approved specific removals for a whole repository. **The problem:** Approved removals still need to be applied across many files without drifting into refactoring or redesign. **The outcome:** Repository-wide cleanup limited to the reviewed scope, with no redesign of dependencies, abstractions, or wrappers. ### Steps 1. Complete the read-only `$deslop deep` audit and record which HIGH items you approve. 2. Start Codex in the target repository root on a clean working tree. 3. Run `$deslop deep apply` to clean up repository-wide within the reviewed scope. 4. Review the diff against the approved list and revert anything outside it. 5. Run the project's test suite and any checks you rely on before committing. (inferred, check the README) ### Prompt to paste into your agent ```text Using the deslop Skill from MrZoyo/deslop-GPT, run `$deslop deep apply` on 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. ``` ### Caveat Apply mode permits scoped edits but does not settle uncertainty in favor of deletion, so anything the audit marked PRESERVE should stay in place. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/mrzoyo-deslop-gpt/apply-reviewed-repo-wide-cleanup/