All skills
softaworks avatar

/reducing-entropy

@1c0662a
by softaworkssoftaworks/agent-toolkit2.5k stars
230

Manual-only skill for minimizing total codebase size. Only activate when explicitly requested by user. Measures success by final code amount, not effort. Bias toward deletion.

Use this Skill: https://skilld.dev/gh/softaworks/agent-toolkit/reducing-entropy

This session only. Nothing lands on disk.

referencesdata-over-abstractions.md

≈474 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Data-Oriented Design

The Core Principle

"It is better to have 100 functions operate on one data structure than 10 functions on 10 data structures."

Generic operations on generic data structures beat specialized operations on specialized structures.

Why Custom Abstractions Hurt

Every custom type, wrapper class, or specialized structure:

  • Adds a concept to understand
  • Requires its own operations
  • Limits composition with other code
  • Creates maintenance burden

A Map<String, Value> can be processed by hundreds of existing functions. A SettingsManager class can only be processed by the methods you write for it.

Information Over Objects

Model the information domain, not the behavior.

  • What data exists?
  • What are the essential relationships?
  • What transformations do you need?

Then use generic structures (maps, vectors, sets) to represent that information. The behavior comes from functions that operate on data - not from methods bound to custom objects.

Practical Application

Before creating a new class/type, ask:

  • Could this be a map/dict with well-known keys?
  • Could this be a simple tuple/record?
  • Do I need custom behavior, or just data?

If you just need data, use data structures. Save custom types for when you genuinely need custom behavior that can't be a function.

The power is in the combinations, not the custom constructs.

External References

Source: SKILL.md on GitHub

No alerts16d5 checks · Risk SAFE
  • Gen Agent Trust Hub16d

    The skill provides a framework for reducing code complexity through deletion and simplification. It is conceptually safe but carries a low risk of indirect prompt injection, as it requires the agent to analyze and modify external codebases that could contain malicious instructions designed to trick the agent into removing security controls.

  • Socket16d

    No alerts

  • Snyk16d

    Risk: LOW · No issues

  • Runlayer7mo

    7 files scanned · No issues

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at 1c0662a. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 months ago.

Dormantupdated 9 months ago
  • Refactoring
  • entropy
  • code-deletion
  • codebase-size
  • minimalism
  • technical-debt
  • architecture

README badge

README badge for softaworks/agent-toolkit/reducing-entropy

Reduces total codebase size by favoring deletion over addition, measuring success by final code amount rather than effort or refactoring elegance. Requires explicit user activation and loading a reference mindset before proceeding; applies to any project where minimizing lines of code is the primary goal, not organizational improvements.

Generated from the current SKILL.md.

When should I activate this skill?
Only when explicitly requested by the user. This is a manual-only skill for focused reduction efforts, not a default mode.
What does 'success' mean for this skill?
Success is measured by final codebase size, not effort or refactoring cleanliness. Writing 50 lines to delete 200 lines is a win.
Does this skill apply to all codebases?
No. Skip it if the codebase is already minimal, if you're constrained by framework conventions or regulatory requirements, or if reduction isn't the stated goal.
How do I use the reference mindsets?
Load at least one mindset from the references/ directory before proceeding. Read the frontmatter descriptions to find which applies, then state which you loaded.

Generated from the current SKILL.md. These answers refresh after source changes.