simplify

A code-cleanup command that makes existing code simpler while keeping its tests passing. It follows rules such as avoiding unnecessary abstractions and removing code that is not needed.

In plain words
What is it for?
Use it to review and refactor code after tests are already passing. It is suited to removing duplication, unnecessary layers, and unused or overly clever solutions.
Why use it?
It helps reduce confusing, overcomplicated code without changing behavior. It also identifies cases where simplification could be unsafe, such as security checks or concurrency code.

Command for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/wbern/agent-instructions/simplify
Clone the repo
git clone --depth 1 https://github.com/wbern/agent-instructions

Made for: Claude Code.

Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 682 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00007 $0.00682
Opus 5 $0.00003 $0.00341
Sonnet 5 $0.00001 $0.00136
Haiku 4.5 $0.00001 $0.00068

Measured 2d ago against content hash 814bfedcfddd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

simplify scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/simplify.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

General Guidelines

Output Style

  • Never explicitly mention TDD in code, comments, commits, PRs, or issues
  • Write natural, descriptive code without meta-commentary about the development process
  • The code should speak for itself - TDD is the process, not the product

Beads is available for task tracking. Use mcp__beads__* tools to manage issues (the user interacts via bd commands).

User arguments:

Simplify: $ARGUMENTS

End of user arguments

(If there was no info above, fallback to the context of the conversation)

Reduce complexity while keeping tests green.

Core Principles

YAGNI - Don't build until actually needed. Delete "just in case" code.

KISS - Simplest solution that works. Clever is the enemy of clear.

Rule of Three - Don't abstract until 3rd occurrence. "Prefer duplication over wrong abstraction" (Sandi Metz).

When NOT to Simplify

  • Essential domain complexity (regulations, business rules)
  • Performance-critical optimized code
  • Concurrency/thread-safety requirements
  • Security-sensitive explicit checks

Prerequisites

Tests must be green. If failing, use /green first.

Code Complexity Signals

Look for these refactoring opportunities:

  • Nesting > 3 levels deep
  • Functions > 20 lines
  • Duplicate code blocks
  • Abstractions with single implementation
  • "Just in case" parameters or config
  • Magic values without names
  • Dead/unused code

Techniques

Pattern Before After
Guard clause Nested if/else Early return
Named condition Complex boolean const isValid = ...
Extract constant if (x > 3) if (x > MAX_RETRIES)
Flatten callback .then().then() async/await

Also apply: Consolidate duplicates, inline unnecessary abstractions, delete dead code.

Validate

  1. Tests still green
  2. Code reads more clearly
  3. No behavioral changes

Simplify removes complexity locally. Refactor improves architecture broadly. Use /refactor if changes require structural reorganization.

Read the full file on GitHub · 96 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 96 lines · 7 tokens per session scan A 814bfedcfddd

Subscribe to this mod's changes

simplify is a command published in the GitHub repository wbern/agent-instructions (168 stars, last pushed 3mo ago), licensed MIT. It adds 7 tokens to every session and 682 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.