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/skillifynpx skills add furkangonel/cowrangler --skill skillifygit 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/skillify)<a href="https://agentmods.dev/skills/furkangonel/cowrangler/skillify"><img src="https://agentmods.dev/badge/skills/furkangonel/cowrangler/skillify.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 | $0.00021 | $0.00860 |
| Opus 5 | $0.00010 | $0.00430 |
| Sonnet 5 | $0.00004 | $0.00172 |
| Haiku 4.5 | $0.00002 | $0.00086 |
Grade A, and why
skillify 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skillify Skill
Goal
Analyze the current session's work, identify the repeatable process within it, and create a well-structured SKILL.md that captures that process for future use.
Steps
1. Identify the repeatable process
Look at what was done in this session:
- What was the user's original request?
- What steps were taken to fulfill it?
- Which steps were mechanical/repeatable vs. one-off judgment calls?
A good skill captures the repeatable mechanical steps and the judgment criteria — not the one-time context.
Success criteria: You can describe the skill in one sentence: "This skill [does what] [when what trigger]."
2. Interview the user (if needed)
Ask:
- "What should trigger this skill in the future?" (the when_to_use)
- "Are there variations of this task I should handle?" (edge cases)
- "What's the most important thing to get right?" (success criteria)
- "Which tools should be available to this skill?" (allowed-tools)
If the session was clear enough, skip to step 3.
Success criteria: You have enough information to write a when_to_use that will trigger reliably.
3. Choose the skill location
- Project-specific (
.cowrangler/skills/<name>/): Workflow is specific to this codebase - Global (
~/.cowrangler/skills/<name>/): Workflow is general-purpose, useful across projects
Ask the user if not obvious.
4. Write the SKILL.md
Follow this template strictly:
---
name: [kebab-case-name]
description: [One line: what it does and when]
when_to_use: Use when [trigger condition]. Triggers include "[example phrase 1]", "[example phrase 2]". Also trigger when [secondary trigger].
argument-hint: "[input the user should provide]"
allowed-tools: [comma-separated list, or omit for all tools]
---
# [Skill Title]
## Goal
[What this skill achieves — the outcome, not the process]
## Steps
### 1. [Step name]
[What to do, concretely]
**Success criteria**: [How you know this step is done correctly]
### 2. [Step name]
...
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 · 101 lines · 21 tokens per session scan A 9c2f5fb01e8e
skillify is a skill published in the GitHub repository furkangonel/cowrangler (2 stars, last pushed 3d ago), licensed MIT. It adds 21 tokens to every session and 860 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。.