market-report

market-report is a skill for Claude Code from OpenCMC/skills-for-ai-agents-by-CoinMarketCap. It costs 100 tokens per session (1,244 once invoked), scanned A, original, MIT.

A workflow for producing a broad cryptocurrency market report from CoinMarketCap data. It combines market size, sentiment, dominance, technical indicators, derivatives information, and other relevant signals.

In plain words
What is it for?
Use it when someone asks how the crypto market is doing, wants a market summary, or asks about sentiment, Bitcoin dominance, altcoin season, or current market narratives.
Why use it?
It gathers several types of market information into one structured review instead of checking each measure separately. The workflow also verifies that the required CoinMarketCap connection is available.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it when someone asks how the crypto market is doing, wants a market summary, or asks about sentiment, Bitcoin dominance, altcoin season, or current market narratives.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/opencmc/skills-for-ai-agents-by-coinmarketcap/market-report
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 OpenCMC/skills-for-ai-agents-by-CoinMarketCap --skill market-report
Clone the repo
git clone --depth 1 https://github.com/OpenCMC/skills-for-ai-agents-by-CoinMarketCap

Made for: Claude Code.

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 market-report

README.md
[![agentmods](https://agentmods.dev/badge/skills/opencmc/skills-for-ai-agents-by-coinmarketcap/market-report/github.svg)](https://agentmods.dev/skills/opencmc/skills-for-ai-agents-by-coinmarketcap/market-report)
Your own site
<a href="https://agentmods.dev/skills/opencmc/skills-for-ai-agents-by-coinmarketcap/market-report"><img src="https://agentmods.dev/badge/skills/opencmc/skills-for-ai-agents-by-coinmarketcap/market-report/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 market-report

Your own site · 80×15
<a href="https://agentmods.dev/skills/opencmc/skills-for-ai-agents-by-coinmarketcap/market-report"><img src="https://agentmods.dev/badge/skills/opencmc/skills-for-ai-agents-by-coinmarketcap/market-report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,244 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 $0.00100 $0.01244
Opus 5 $0.00050 $0.00622
Sonnet 5 $0.00020 $0.00249
Haiku 4.5 $0.00010 $0.00124

Measured 12d ago against content hash de2bd3cda070, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

market-report 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 12d 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/market-report/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Market Report Skill

Generate a comprehensive crypto market report by systematically pulling data from multiple CMC MCP tools.

Prerequisites

Before generating a report, verify the CMC MCP tools are available. If tools fail or return connection errors, ask the user to set up the MCP connection:

{
  "mcpServers": {
    "cmc-mcp": {
      "url": "https://mcp.coinmarketcap.com/mcp",
      "headers": {
        "X-CMC-MCP-API-KEY": "your-api-key"
      }
    }
  }
}

Get your API key from https://pro.coinmarketcap.com/login

Core Principle

Fetch data from all relevant tools to provide a complete market picture. Users want a one-stop summary they can rely on daily.

Report Workflow

Step 1: Global Market Health

Call get_global_metrics_latest to get:

  • Total crypto market cap and 24h/7d/30d changes
  • Fear & Greed Index (current value and trend)
  • Altcoin Season Index
  • BTC and ETH dominance
  • Total volume
  • ETF flows (BTC and ETH)

Step 2: Market Technical Analysis

Call get_crypto_marketcap_technical_analysis to get:

  • Total market cap RSI
  • MACD signals
  • Key support/resistance levels (Fibonacci, pivot points)

Step 3: Leverage and Derivatives

Call get_global_crypto_derivatives_metrics to get:

  • Total open interest and changes
  • Funding rates (positive = longs paying shorts)
  • BTC liquidations (long vs short bias)
  • Futures vs perpetuals breakdown

Step 4: Trending Narratives

Call trending_crypto_narratives to get:

  • Top trending themes/sectors
  • Market cap and performance of each narrative
  • Top coins within each narrative

Step 5: Upcoming Catalysts

Call get_upcoming_macro_events to get:

  • Fed meetings and rate decisions
  • Regulatory deadlines
  • Major protocol upgrades
  • Other market-moving events

Step 6: BTC and ETH Quick Check

Call get_crypto_quotes_latest with id="1,1027" to get current BTC and ETH prices and changes as anchors for the report.

Report Structure

Present the data in this order:

## Market Snapshot
- Total market cap: $X.XX T (24h: +X.X%)
- Fear & Greed: XX (Extreme Fear/Fear/Neutral/Greed/Extreme Greed)
- BTC Dominance: XX% | ETH Dominance: XX%
- Altcoin Season Index: XX

## BTC & ETH
- BTC: $XX,XXX (24h: X.X%, 7d: X.X%)
- ETH: $X,XXX (24h: X.X%, 7d: X.X%)

## Market Technicals
- RSI: XX (oversold/neutral/overbought)
- MACD: bullish/bearish
- Key levels: support at $X.XX T, resistance at $X.XX T

## Leverage & Sentiment
- Open Interest: $XXX B (24h: X.X%)
- Funding Rate: X.XXX% (longs/shorts paying)
- 24h Liquidations: $XXX M (XX% longs, XX% shorts)

## Trending Narratives
1. Narrative Name - $XX B market cap, +XX% (7d)
2. ...

## Upcoming Catalysts
- Date: Event description
- ...

Read the full file on GitHub · 145 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. 12d ago First seen · 145 lines · 100 tokens per session scan A de2bd3cda070

Subscribe to this mod's changes

market-report is a skill published in the GitHub repository OpenCMC/skills-for-ai-agents-by-CoinMarketCap (67 stars, last pushed 6mo ago), licensed MIT. It adds 100 tokens to every session and 1,244 once invoked, about $0.0005 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.