agentmods.dev

yellow-pro

yellow-pro is a skill for Claude Code, Codex from layer-3/yellow-pro-mcp. It costs 56 tokens per session (656 once invoked), scanned A, original, MIT.

A command-line tool for the YellowPro cryptocurrency exchange.

In plain words
What is it for?
Checking markets, prices, order books, balances, positions, funding, orders, and trades, plus placing or cancelling orders.
Why use it?
It gives an agent one way to view exchange data and account information, or trade when trading is enabled.

Skill for Claude CodeCodex

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

not rated 0repo 2mo ago A scan 56 tokens original MIT

Good fit Checking markets, prices, order books, balances, positions, funding, orders, and trades, plus placing or cancelling orders.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/layer-3/yellow-pro-mcp/yellow-pro
View source ↗ layer-3/yellow-pro-mcp
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 layer-3/yellow-pro-mcp --skill yellow-pro
Clone the repo
git clone --depth 1 https://github.com/layer-3/yellow-pro-mcp

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 yellow-pro

README.md
[![agentmods](https://agentmods.dev/badge/skills/layer-3/yellow-pro-mcp/yellow-pro/github.svg)](https://agentmods.dev/skills/layer-3/yellow-pro-mcp/yellow-pro)
Your own site
<a href="https://agentmods.dev/skills/layer-3/yellow-pro-mcp/yellow-pro"><img src="https://agentmods.dev/badge/skills/layer-3/yellow-pro-mcp/yellow-pro/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for yellow-pro

Your own site · 80×15
<a href="https://agentmods.dev/skills/layer-3/yellow-pro-mcp/yellow-pro"><img src="https://agentmods.dev/badge/skills/layer-3/yellow-pro-mcp/yellow-pro.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 656 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 $0.00056 $0.00656
Opus 5.5 $0.00022 $0.00262
Sonnet 5.5 $0.00011 $0.00131
Haiku 4.5 $0.00006 $0.00066

Measured 2mo ago against content hash 517b586c5c90, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

yellow-pro 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 2mo 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.

skills/yellow-pro/SKILL.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

yellow_pro exchange CLI

The yellow-pro CLI wraps the yellow_pro REST API. All output is raw exchange JSON. Prefer the yellow_pro MCP server when available; this CLI covers the same surface.

Requirements

Environment variables (already set if the MCP server is configured):

  • YELLOW_PRO_API_KEY, YELLOW_PRO_API_SECRET, YELLOW_PRO_APP_SESSION_ID — for account/trading commands
  • YELLOW_PRO_ENABLE_TRADING=true — required for place/cancel/leverage/transfer commands
  • YELLOW_PRO_BASE_URL — optional explicit URL override
  • YELLOW_PRO_SANDBOX=true — use staging (https://api.staging.yellow.pro.neodax.app); otherwise production (https://trade.api.yellow.pro)

Workflow

  1. Discover markets first: yellow-pro markets — native ids look like ETHUSDT (spot) and BTCUSDT-PERP (perpetual). Check precision/filters before quoting amounts.
  2. Market data: yellow-pro ticker <market>, yellow-pro orderbook <market>, yellow-pro klines <market> --interval 1h --limit 100, yellow-pro funding <market>
  3. Account: yellow-pro balance spot or yellow-pro balance perp, yellow-pro open-orders perp, yellow-pro positions, yellow-pro trades perp --market <market>, yellow-pro fee-tier
  4. Trading (amounts/prices are decimal strings). For both Spot and Perpetual markets, an order amount is quantity in the market's base asset: ETHUSDT uses ETH and BTCUSDT-PERP uses BTC. Prices use the market's quote asset. Label both values with their correct units when confirming.
    • yellow-pro place perp BTCUSDT-PERP buy limit 0.001 65000 --leverage 5 --client-order-id my-id
    • yellow-pro place spot ETHUSDT sell market 0.01
    • yellow-pro cancel perp BTCUSDT-PERP <order_uuid>
    • yellow-pro cancel-all perp --market BTCUSDT-PERP
    • yellow-pro close-positions --market BTCUSDT-PERP
    • yellow-pro set-leverage BTCUSDT-PERP 10
  5. Run yellow-pro --help for the full command list.

Safety

  • Never place orders unless the user explicitly asked for them in this conversation.
  • Confirm market id, side, amount (quantity in the market's base asset), and price back to the user before placing an order.
  • If a trading command fails with "trading is disabled", tell the user to set YELLOW_PRO_ENABLE_TRADING=true — do not work around it.

Read the full file on GitHub · 47 lines

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. 2mo ago First seen · 47 lines · 56 tokens per session scan A 517b586c5c90

Subscribe to this mod's changes

yellow-pro is a skill published in the GitHub repository layer-3/yellow-pro-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 56 tokens to every session and 656 once invoked, about $0.0002 per session on Opus 5.5. 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.

Finance and fintechWeb3 and blockchain
Related

yellow-pro compared with skills from other repositories

yellow-pro next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
yellow-prolayer-3/yellow-pro-mcpSkill02mo agoMITA56Claude Code, Codex
agentic-streetLeoYeAI/openclaw-master-skillsSkill2.2k6d agoMITA91Claude Code, Codex
token-pickaeonfun/aeonSkill788yesterdayMITA25Claude Code, Codex
bridgealsk1992/CloddsBotSkill3.1k1mo agoMITA13Claude Code, Codex
hyperliquidalsk1992/CloddsBotSkill3.1k1mo agoMITA19Claude Code, Codex
marginfialsk1992/CloddsBotSkill3.1k1mo agoMITA11Claude Code, Codex
airdrop-hunting-guidenirholas/three.wsSkill269yesterdayApache-2.0A54Claude Code, Codex