simplify-code

Reviews recent code changes with four parallel subagents and applies safe cleanup fixes.

Updated Sep 10, 2026
One-click install
npx skills add https://github.com/loteiron/ZeusAgent --skill simplify-code-loteiron
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: simplify-code
Source: https://github.com/loteiron/ZeusAgent/tree/main/skills/software-development/simplify-code
Command: npx skills add https://github.com/loteiron/ZeusAgent --skill simplify-code-loteiron

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Recent code changes often accumulate duplication, needless complexity, wasted work, and shallow band-aid fixes that a single broad review misses. This Skill runs four focused reviewers in parallel over your diff, aggregates their findings, and applies only the fixes worth applying. ## Core Features & Use Cases - Parallel 4-Agent Review: Launches reuse, quality, efficiency, and altitude reviewers concurrently via delegate_task batch mode, each searching the full codebase for evidence. - Risk-Tiered Application: Auto-applies SAFE fixes, verifies CAREFUL fixes with tests, and flags RISKY changes (public API renames, N+1 restructuring) for human review. - Flexible Scoping: Supports focus filters (reuse, quality, efficiency, altitude), dry-run mode, and diff scoping (staged, last commit, branch, specific files). - Use Case: After finishing a feature branch, ask to simplify your changes; the Skill reviews the diff, removes duplicated logic and dead code, flattens nested conditionals, and reports deeper infrastructure fixes worth a follow-up task. ## Quick Start Ask the agent to simplify my recent changes and apply the safe fixes after running the project tests.

Frequently Asked Questions about simplify-code

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I clean up my recent code changes automatically?▼

Ask the agent to simplify your changes. It captures the git diff, runs four parallel reviewers for reuse, quality, efficiency, and altitude, then applies SAFE fixes automatically and CAREFUL fixes with test verification.

How to review a git diff with multiple subagents in parallel?▼

The Skill uses delegate_task batch mode to launch four reviewers concurrently, each receiving the complete diff plus the repo path. Batch mode returns all findings together, so you pay the latency of one review instead of four.

Can I run a code cleanup review without changing any files?▼

Yes, request a dry run by saying simplify but do not change anything. The four reviewers still run and present findings grouped by risk tier, but nothing is applied until you approve.

Does this work if subagent delegation is unavailable?▼

Yes, it falls back to a single-pass inline review covering all four angles sequentially in the current context. The final summary clearly states it was an inline review rather than the parallel fan-out.

When should I not use a parallel cleanup review?▼

Avoid it for hunting correctness bugs, which belongs in a dedicated code review pass, and for very large diffs over roughly 2000 lines without scoping down first. It also should not run automatically after every edit since it costs four subagents of tokens.