modeling-behavior-refactor

modeling-behavior-refactor is a skill for Claude Code, Codex from mantou6666/Math-Modeling-Agent-Flow. It costs 38 tokens per session (111 once invoked), scanned A, original, MIT.

A code-simplification method for contest-style software that preserves its mathematical results, numerical behavior, and speed-sensitive operations.

In plain words
What is it for?
It is for comparing executable versions, checking result identifiers and values, and running regression and independent-evaluator checks within a stated tolerance.
Why use it?
It helps reduce unnecessary code structure while checking that simplification does not change evaluated results or performance-critical behavior.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for comparing executable versions, checking result identifiers and values, and…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mantou6666/math-modeling-agent-flow/modeling-behavior-refactor
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.

Any agent
npx skills add mantou6666/Math-Modeling-Agent-Flow --skill modeling-behavior-refactor
Clone the repo
git clone --depth 1 https://github.com/mantou6666/Math-Modeling-Agent-Flow

Made for: Claude Code, Codex.

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 modeling-behavior-refactor

README.md
[![agentmods](https://agentmods.dev/badge/skills/mantou6666/math-modeling-agent-flow/modeling-behavior-refactor.svg)](https://agentmods.dev/skills/mantou6666/math-modeling-agent-flow/modeling-behavior-refactor)
Your own site
<a href="https://agentmods.dev/skills/mantou6666/math-modeling-agent-flow/modeling-behavior-refactor"><img src="https://agentmods.dev/badge/skills/mantou6666/math-modeling-agent-flow/modeling-behavior-refactor.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 111 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 $0.00038 $0.00111
Opus 5 $0.00019 $0.00056
Sonnet 5 $0.00008 $0.00022
Haiku 4.5 $0.00004 $0.00011

Measured 7d ago against content hash 03ef4ad99f33, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

modeling-behavior-refactor 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.

math-modeling-finalizer/skills/modeling-behavior-refactor/SKILL.md · 9 lines

What it actually says

Contestant-scale code simplification

Compare baseline and current executable hashes. Simplify only unnecessary engineering structure. Preserve mathematical kernels, formal evaluator, numerical stability and performance-critical vectorization. After changes, compare official Result IDs/values, feasibility, key intermediates and independent evaluator outputs within declared tolerance. No freeze/state-machine dependency is required.

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 · 9 lines · 38 tokens per session scan A 03ef4ad99f33

Subscribe to this mod's changes

modeling-behavior-refactor is a skill published in the GitHub repository mantou6666/Math-Modeling-Agent-Flow (16 stars, last pushed 17d ago), licensed MIT. It adds 38 tokens to every session and 111 once invoked, about $0.0002 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.