abstraction

abstraction is an agent for Claude Code from JhonatanRian/gemini-simplify-extension. It costs 20 tokens per session (252 once invoked), scanned B, original, MIT.

A code-review agent that looks for reusable code, duplicated logic, and opportunities to use built-in library functions.

In plain words
What is it for?
Use it to find existing utilities, flag copy-pasted code, suggest shared abstractions, and identify apparently unused functions, classes, or imports.
Why use it?
It helps prevent the codebase from growing repeated or unnecessary implementations. It checks that suggested helpers actually exist before recommending them.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

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 agents/jhonatanrian/gemini-simplify-extension/abstraction
Clone the repo
git clone --depth 1 https://github.com/JhonatanRian/gemini-simplify-extension

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 abstraction

README.md
[![agentmods](https://agentmods.dev/badge/agents/jhonatanrian/gemini-simplify-extension/abstraction.svg)](https://agentmods.dev/agents/jhonatanrian/gemini-simplify-extension/abstraction)
Your own site
<a href="https://agentmods.dev/agents/jhonatanrian/gemini-simplify-extension/abstraction"><img src="https://agentmods.dev/badge/agents/jhonatanrian/gemini-simplify-extension/abstraction.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 252 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 5.1 $0.00020 $0.00252
Opus 5 $0.00010 $0.00126
Sonnet 5 $0.00004 $0.00050
Haiku 4.5 $0.00002 $0.00025

Measured 5d ago against content hash 77d0d7e69062, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

abstraction scanned grade B with 1 finding 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 5d 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.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

tools: ["*"]
agents/abstraction.md · 20 lines

What it actually says

Abstraction & Reuse Analyst

Objective: Identify opportunities for code reuse and standard library alignment. Output a structured report only. Do not modify files.

Verification Protocol:

  • Before suggesting the use of an existing utility, you MUST verify the file's existence and the function's signature using read_file or grep_search. Do not assume a utility exists just because it has a common name.

Universal Directives:

  1. Existing Utilities & Helpers: Find existing functions in the codebase that can replace new logic. Provide the file path and line number of the existing utility as evidence.
  2. Duplication Flagging: Report any new logic that duplicates existing functionality.
  3. Inline Logic Consolidation: Identify hand-rolled logic that should be replaced by native standard library functions.
  4. Copy-Paste Variations: Detect near-duplicate blocks and suggest a shared abstraction.
  5. Dead Code Detection: Identify functions, classes, or imports that appear to be unused within the current scope and flag them for removal in the Cleanup phase.
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. 5d ago First seen · 20 lines · 20 tokens per session scan B 77d0d7e69062

Subscribe to this mod's changes

abstraction is an agent published in the GitHub repository JhonatanRian/gemini-simplify-extension (1 stars, last pushed 4mo ago), licensed MIT. It adds 20 tokens to every session and 252 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.