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/justvugg/tools-factory/coingeckonpx skills add JustVugg/tools-factory --skill coingeckogit clone --depth 1 https://github.com/JustVugg/tools-factoryWrote 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/justvugg/tools-factory/coingecko)<a href="https://agentmods.dev/skills/justvugg/tools-factory/coingecko"><img src="https://agentmods.dev/badge/skills/justvugg/tools-factory/coingecko.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 5.1 | $0.00038 | $0.00445 |
| Opus 5 | $0.00019 | $0.00222 |
| Sonnet 5 | $0.00008 | $0.00089 |
| Haiku 4.5 | $0.00004 | $0.00044 |
Grade A, and why
coingecko 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 6d 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.
What it actually says
coingecko
Generated by Gutenberg. Use this skill to call the coingecko API through the local coingecko CLI.
When to use
- The user asks for data exposed by coingecko (api).
- An agent task needs structured JSON from https://api.coingecko.com.
- You need to perform a write/destructive operation on coingecko — always preview first, run with
--yesonly on explicit user confirmation.
How to invoke
The skill assumes the generated CLI is on PATH (or invoke via scripts/use-go.sh run ./cmd/coingecko from the project directory).
coingecko operations
coingecko call getCoinsMarkets --json
coingecko sync --json
coingecko search "<keyword>" --json
Authentication
No authentication required.
Operations index
getCoinsMarkets(GET /api/v3/coins/markets) — read — GET /api/v3/coins/marketsgetCoinsBitcoin(GET /api/v3/coins/bitcoin) — read — GET /api/v3/coins/bitcoingetSimplePrice(GET /api/v3/simple/price) — read — GET /api/v3/simple/pricegetGlobal(GET /api/v3/global) — read — GET /api/v3/global
Output contract
- All commands accept
--jsonand emit machine-readable output. callreturns{ dryRun, operation, request, response }.dryRun: truemeans the call was not executed (write op without--yes).searchreturns cached records.syncpopulates the local SQLite cache.
Provenance
- Schema: gutenberg.blueprint.v1
- Generated by: gutenberg 0.3.0
- Source spec: /tmp/coingecko.openapi.json
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.
- 6d ago First seen · 51 lines · 38 tokens per session scan A d7eea784f2af
coingecko is a skill published in the GitHub repository JustVugg/tools-factory (52 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 445 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.
Other skills, from other repositories
stock-share-chg
查询 A 股股东增减持明细。当用户需要获取 A 股股东增减持数据（按 stockcode 分页查询全部历史，或以 islast=true 查全市场最新一期），支持沪深京股票时使用。.
cb-base-data
单只可转债基础信息（market.ft.tech）。用户问可转债基础信息、转债详情、某只可转债、转股价、转股价值、到期日、发行规模时使用。.
eastmoney-market-valuation
查询东财市场日估值。当用户需要查询 A 股主要市场指数（上证指数、沪深300、深证成指、创业板指、科创50、北证50）的每日估值数据，包括市盈率、总市值、流通市值、收盘点位等；支持单日、区间查询，或了解东财市场日估值时使用。.
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。.
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。.
hsi-daily-weight
查询恒生系列指数成份股权重（HSI 恒生指数 / HSCEI 国企指数 / HSAIT 等）。按交易日/日期范围/指数/股票过滤。Use when user asks about 港股指数权重, 恒生指数成份股权重, 国企指数权重, 恒生科技权重, hsi daily weight, 港股权重. 注意：HSAIT 的"恒生科技"映射存疑（见注意事项），HSI/HSCEI 可用。.