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.
npx agentmods add skills/furkangonel/cowrangler/simplifynpx skills add furkangonel/cowrangler --skill simplifygit clone --depth 1 https://github.com/furkangonel/cowranglerWrote 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.
[](https://agentmods.dev/skills/furkangonel/cowrangler/simplify)<a href="https://agentmods.dev/skills/furkangonel/cowrangler/simplify"><img src="https://agentmods.dev/badge/skills/furkangonel/cowrangler/simplify.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00025 | $0.00873 |
| Opus 5 | $0.00013 | $0.00436 |
| Sonnet 5 | $0.00005 | $0.00175 |
| Haiku 4.5 | $0.00003 | $0.00087 |
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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Simplify Skill
Goal
Run a focused quality audit on the code changed in the current session (or specified files), identify reuse/quality/efficiency issues, then fix them — all without changing external behavior.
Philosophy
- Behavior is sacred: Never change what the code does, only how it does it
- Prefer deletion: The best code is code you don't have to maintain
- Three lenses: Code Reuse (DRY), Code Quality (readability, correctness), Efficiency (performance, bundle size)
Steps
1. Identify changed code
Run git diff --name-only HEAD (or the specified files) to get the scope.
If no git changes and no files specified, ask the user which files to audit.
Success criteria: You have a clear list of files/functions to audit.
2. Launch parallel audit agents
Use spawn_subagent_parallel with three agents running simultaneously:
Agent 1 — Code Reuse (explore) Task: Find duplication in the changed files. Look for:
- Functions/logic duplicated elsewhere in the codebase
- Inline code that should be extracted into utilities
- Repeated patterns that could use existing libraries
- Constants that are hardcoded instead of referenced
Agent 2 — Code Quality (code-reviewer) Task: Identify quality issues in the changed files. Look for:
- Unclear variable/function names
- Missing or incorrect error handling
- Functions doing too many things (SRP violations)
- Commented-out code or dead branches
- Type safety issues (any, implicit any, missing return types)
Agent 3 — Efficiency (performance) Task: Find performance and efficiency issues in the changed files. Look for:
- Unnecessary re-computation inside loops
- Missing memoization for expensive operations
- Synchronous blocking where async would work
- Large imports when only small parts are used
- Memory leaks (event listeners, timers, subscriptions not cleaned up)
Success criteria: All three agents complete and return findings.
3. Triage findings
Collect all findings from the three agents. Categorize each as:
- Fix now — clear improvement, zero risk of behavior change
- Discuss — might be improvement but has trade-offs (share with user)
- Skip — out of scope or not worth the churn
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.
- 4d ago First seen · 88 lines · 25 tokens per session scan A deb53cf077ad
simplify is a skill published in the GitHub repository furkangonel/cowrangler (2 stars, last pushed 3d ago), licensed MIT. It adds 25 tokens to every session and 873 once invoked, about $0.0001 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.
Other skills, from other repositories
eastmoney-stock-valuation
查询东财个股日估值。当用户需要查询全部 A 股个股的每日估值数据，包括市盈率（TTM/LYR）、市净率、市现率、市销率、PEG、总市值、流通市值、收盘价等；支持单票单日、单票历史区间及全市场查询，或了解东财个股日估值时使用。.
stock-quotes-list
查询 A 股行情列表（分页）。当用户需要获取 A 股（沪深京）股票行情列表，支持按板块筛选、多字段排序与分页，用于行情中心「个股行情」等列表展示，或了解A 股行情列表（分页）时使用。.
eastmoney-us-stock-daily-ohlc
查询东财美股历史日 K 线。当用户需要查询东财美股历史日 K 线；有日期范围时按 3 天窗口分批请求，无日期范围时全量拉取，或了解东财美股历史 OHLC、东财美股历史日 K 线时使用。.
etf-list-paginated
ETF 分页列表，支持分页、排序、筛选（market.ft.tech）。用户问 ETF 列表、全市场 ETF、按涨跌幅排序的 ETF、筛选某类 ETF 时使用。.
etf-ohlcs
单只 ETF OHLC K 线（market.ft.tech）。用户问某只 ETF 的 K 线、日线/周线/月线、开高低收、前/后复权时使用。.
etf-prices
单只 ETF 分钟级分时价格（market.ft.tech）。用户问某只 ETF 分时、当日走势、多日分时、一分钟行情时使用。.