quality-screener-mcp-server: Skill for Claude Code

.claude/skills/code-simplifier/SKILL.md

code-simplifier-backend is a skill for Claude Code from quality-screener/quality-screener-mcp-server. It costs 88 tokens per session (2,477 once invoked), scanned A, original, MIT.

A code-cleanup workflow for Python backend code, including FastAPI routes and related services. It makes the code easier to read and maintain while keeping its observable behavior unchanged.

In plain words
What is it for?
Use it to simplify backend code, reduce complexity, refactor for clarity, or review recently changed Python code for maintainability.
Why use it?
It helps remove unnecessary complexity, deep nesting, unclear names, and dead code without changing what the backend does.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is quality-screener/quality-screener-mcp-server's own configuration. It tells Claude Code how to work on quality-screener-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything quality-screener-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to quality-screener/quality-screener-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/quality-screener/quality-screener-mcp-server/main/.claude/skills/code-simplifier/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/quality-screener/quality-screener-mcp-server

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for code-simplifier-backend

README.md
[![agentmods](https://agentmods.dev/badge/skills/quality-screener/quality-screener-mcp-server/code-simplifier.svg)](https://agentmods.dev/skills/quality-screener/quality-screener-mcp-server/code-simplifier)
Your own site
<a href="https://agentmods.dev/skills/quality-screener/quality-screener-mcp-server/code-simplifier"><img src="https://agentmods.dev/badge/skills/quality-screener/quality-screener-mcp-server/code-simplifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,477 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00088 $0.02477
Opus 5 $0.00044 $0.01239
Sonnet 5 $0.00018 $0.00495
Haiku 4.5 $0.00009 $0.00248

Measured 7d ago against content hash 989c82d42f40, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

code-simplifier-backend 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 7d 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/skills/code-simplifier/SKILL.md · 306 lines

How it starts

The opening of the file, as written. The whole thing — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Backend Code Simplifier

Expert simplification of Python backend code. Make the code easier to read, safer to evolve, and more consistent with project standards — without changing observable behavior.

Core Goal

Preserve functionality exactly while reducing accidental complexity.

Prefer explicit, boring, maintainable Python over clever or overly compact code. A few extra lines that read top-to-bottom are almost always better than a dense expression that requires a debugger to understand.

Mental Model — "Make It Boring"

When in doubt, ask:

  1. Can a new reader summarize this function in one sentence? If not, split it.
  2. Does the happy path read top-to-bottom without diving into branches? If not, hoist guard clauses and flatten nesting.
  3. Is every name a noun for data, a verb for action? If not, rename.
  4. Does the abstraction earn its keep at this call site count? If only one caller uses it, inline it. If three+ callers use a near-duplicate, extract it.
  5. Could you delete this code and still pass the tests? If yes, delete it.

Project Standards (Non-negotiable)

  • Keep full type annotations on functions; do not drop them to "simplify".
  • Keep Google-style docstrings where the codebase has them.
  • Respect existing service-layer and module boundaries (api/, analysis/, financial/, database/).
  • Reuse existing helpers and patterns before introducing new abstractions.
  • Reuse research/ prototypes when the simplification target maps to one.
  • Keep changes pytest-friendly; do not break fixtures or test seams.
  • Do not run ruff or type checking unless the user explicitly asks.

Simplification Priorities (In Order)

1. Preserve Behavior — Always

Do not change API contracts, database semantics, scheduling cadence, auth behavior, numerical/financial logic, or response shapes unless the user asks for a behavioral change. When uncertain, ask before editing.

2. Reduce Complexity

  • Flatten deeply nested conditionals; prefer guard clauses and return early.
  • Replace "do everything" functions with smaller helpers — but only when the split is natural (one clear noun/verb each), not just to lower line counts.
  • Remove duplicated logic; consolidate near-duplicate branches.
  • Eliminate one-use abstractions, pass-through wrappers, and needless indirection.
  • Replace boolean-flag pyramids with explicit control flow or enum dispatch.
  • Break apart dense comprehensions / chained expressions when readability suffers.
  • Prefer table-driven dispatch (dict / match) over long if/elif ladders.

Read the full file on GitHub · 306 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. 7d ago First seen · 306 lines · 88 tokens per session scan A 989c82d42f40

Subscribe to this mod's changes

code-simplifier-backend is a skill published in the GitHub repository quality-screener/quality-screener-mcp-server (0 stars, last pushed 3d ago), licensed MIT. It adds 88 tokens to every session and 2,477 once invoked, about $0.0004 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.