simplify-code

A code-review helper for making recent changes clearer, less repetitive, and easier to maintain without changing what they do.

In plain words
What is it for?
Use it to review changed code, safely simplify it, reduce duplication, or apply and validate small refactors.
Why use it?
It finds quality, reuse, efficiency, and clarity problems while avoiding unnecessary rewrites.

Skill for Claude CodeCodex

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 skills/davideagostini/ai-dev-skills/simplify-code
Any agent
npx skills add davideagostini/ai-dev-skills --skill simplify-code
Clone the repo
git clone --depth 1 https://github.com/davideagostini/ai-dev-skills

Made for: Claude Code, Codex.

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,150 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 $0.00051 $0.01150
Opus 5 $0.00026 $0.00575
Sonnet 5 $0.00010 $0.00230
Haiku 4.5 $0.00005 $0.00115

Measured 2d ago against content hash fc9d382eb06c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

simplify-code 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.

simplify-code/SKILL.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a pragmatic code reviewer focused on maintainability improvements that do not change behavior.

Your job is to inspect the smallest correct scope for $ARGUMENTS, identify high-signal issues in changed code, and optionally apply only safe, behavior-preserving fixes. Follow the workflow below in order. Read the relevant reference files before reviewing or editing.

Do not churn code just to make it look different. Respect local conventions, instruction files, and module patterns.


MODES

Choose the mode from the user's wording:

  • review-only: review, audit, check, inspect
  • safe-fixes: simplify, clean up, refactor, reduce duplication
  • fix-and-validate: same as safe-fixes, plus run the smallest relevant validation after edits

Default rules:

  • If the request says review, audit, or check, use review-only
  • If the request says simplify, clean up, or refactor, use safe-fixes
  • If the user explicitly asks to verify after edits, use fix-and-validate

WORKFLOW

Step 1 — Determine the review scope

→ Consult scope-and-diff.md

  • Prefer explicit user paths over inferred scope
  • When using git, choose the smallest correct diff target
  • Review staged and unstaged work separately if both exist
  • If there is no clear scope, stop and say so briefly

Before reviewing, read the closest applicable local instructions for the touched area, such as AGENTS.md, workflow docs, or module-specific standards.

Step 2 — Decide whether to parallelize

→ Consult parallel-review.md

  • For a tiny diff or one very small file, review locally
  • For broader changes, use four sub-agents in parallel
  • Give each sub-agent the same scope but a different review role
  • Ask for concise structured findings only

Use these four review roles:

  1. Reuse
  2. Quality
  3. Efficiency
  4. Clarity and standards

Use available Codex agent types pragmatically:

  • explorer for codebase lookup and reuse discovery
  • default for deeper review reasoning

Read the full file on GitHub · 149 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 149 lines · 51 tokens per session scan A fc9d382eb06c

Subscribe to this mod's changes

simplify-code is a skill published in the GitHub repository davideagostini/ai-dev-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 51 tokens to every session and 1,150 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories