Skip to content
Back to search

reclaim-code-entropy

An evidence-first Agent Skill for safely simplifying any codebase.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/yevanchen--reclaim-code-entropy/badge.svg)](/listings/yevanchen--reclaim-code-entropy)

HTML

<a href="/listings/yevanchen--reclaim-code-entropy"><img src="/api/listings/yevanchen--reclaim-code-entropy/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Option A: Codex skill installer (recommended)

Ask Codex:

Install the reclaim-code-entropy skill from https://github.com/Yevanchen/reclaim-code-entropy/tree/main/skills/reclaim-code-entropy

Start a new Codex task after installation.

Option B: Manual install

git clone https://github.com/Yevanchen/reclaim-code-entropy.git
mkdir -p ~/.codex/skills
cp -R reclaim-code-entropy/skills/reclaim-code-entropy ~/.codex/skills/

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 107 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Reclaim Code Entropy
  2. > An evidence-first Agent Skill for safely simplifying any codebase.
  3. English | [简体中文](./README.zh.md)
  4. ## The Problem
  5. Codebases accumulate more than dead symbols. They accumulate duplicate truths, abandoned extension points, compatibility paths with no remaining consumer, lifecycle flags that describe the same transition, and wrappers that only move complexity around.
  6. Static analysis can produce candidates. It cannot prove that a string-dispatched route, public export, migration, persisted format, plugin entrypoint, or asynchronous cleanup path is safe to remove.
  7. ## The Solution
  8. `reclaim-code-entropy` makes simplification evidence-driven:
  9. | Stage | Question |
  10. | --- | --- |
  11. | **Establish the contract** | What is public, persisted, generated, dynamic, or compatibility-sensitive? |
  12. | **Survey entropy** | Where are the extra representations, states, APIs, layers, and policies? |
  13. | **Prove the cut** | Who consumes it, why was it added, and what capability would disappear? |
  14. | **Simplify one boundary** | Can the obsolete contract be removed end to end without replacement glue? |
  15. | **Verify behavior** | What is the smallest check that would fail if the deletion were wrong? |
  16. The skill prefers a few proved cuts over a long speculative cleanup list. Finding nothing safe to remove is a valid result.
  17. ## What It Finds
  18. - unconsumed APIs, exports, config, events, and packages
  19. - mirrored state and duplicate representations of one fact
  20. - speculative abstractions, fixed knobs, and abandoned fallbacks
  21. - forwarding-only wrappers and multiple routes to one behavior
  22. - duplicated lifecycle state, readiness, cancellation, or cleanup
  23. - defensive code on non-boundary, same-process typed handoffs
  24. - hand-rolled infrastructure already covered by the platform
  25. - test- or documentation-only residue from removed implementations
  26. - code added for an idea that was later abandoned incompletely
  27. ## Modes
  28. **Audit mode** ranks candidates by confidence, risk, tradeoff, and estimated net reduction. It does not edit the repository.
  29. **Apply mode** implements the safest proved cut, preserves observable behavior, and runs proportional verification.
  30. ## Install
  31. ### Option A: Codex skill installer (recommended)
  32. Ask Codex:
  33. ```text
  34. Install the reclaim-code-entropy skill from https://github.com/Yevanchen/reclaim-code-entropy/tree/main/skills/reclaim-code-entropy
  35. ```
  36. Start a new Codex task after installation.
  37. ### Option B: Manual install
  38. ```bash
  39. git clone https://github.com/Yevanchen/reclaim-code-entropy.git
  40. mkdir -p ~/.codex/skills
  41. cp -R reclaim-code-entropy/skills/reclaim-code-entropy ~/.codex/skills/
  42. ```
  43. ## Use
  44. Audit a repository without changing it:
  45. ```text
  46. Use $reclaim-code-entropy to audit this repository and rank the safest simplification candidates.
  47. ```
  48. Apply the strongest safe cut:
  49. ```text
  50. Use $reclaim-code-entropy to simplify this repository. Preserve public and persisted behavior, implement one high-confidence cut, and verify it.
  51. ```
  52. Investigate a specific area:
  53. ```text
  54. Use $reclaim-code-entropy to check whether these lifecycle flags represent distinct states or duplicated ownership.
  55. ```
  56. ## Key Insight
  57. Deletion volume is not the goal. The goal is reducing the number of facts, contracts, states, and concepts the team must keep coherent.
  58. A large deletion can be wrong. A small deletion can remove an entire maintenance obligation. The decisive evidence is the consumer graph, ownership model, history, compatibility surface, and verification boundary.
  59. ## How to Know It Is Working
  60. A useful result is reviewable, reduces concepts without hiding compatibility risk, and may still conclude that no safe cut exists.
  61. ## Safety Boundaries
  62. The skill does not simplify away authorization, trust-boundary validation, accessibility basics, data-loss prevention, durable-data compatibility, or cleanup required for resource quiescence.
  63. It is not a performance audit unless simplification is the stated goal.
  64. ## Inspiration
  65. The initial idea came from studying [DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness/commits/master/) and its emphasis on simplification during agent-driven development. This project generalizes that lesson for repositories in any language or stack. It is independent and not affiliated with DeepSeek.
  66. ## License
  67. MIT

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.