Atlas / Skills / jeremylongshore / Tracking Crypto Prices

Tracking Crypto PricesSAFE

skills/jeremylongshore/tracking-crypto-prices

Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.

Verdict
SAFE
Grade
B
Trust score
89 /100
Version
1.27.0
Hosts
1 documented
License
MIT
Stars
2,823
01

Overview

Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.

Read from source at commit 4f83675ca38aOBSERVED · 2026-10-08
02

Install

Commands as the repository documents them. They are shown, not run.

pip install requests pandas yfinance
pip install pyyaml python-dotenv
03

Host compatibility

What the documentation claims. We have not run a compatibility test.

HostStatusNotes
claude-codementioned
04

What it tells the agent

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: tracking-crypto-prices
description: 'Track real-time cryptocurrency prices across exchanges with historical
  data and alerts.

  Provides price data infrastructure for dependent skills (portfolio, tax, DeFi, arbitrage).

  Use when checking crypto prices, monitoring markets, or fetching historical price
  data.

  Trigger with phrases like "check price", "BTC price", "crypto prices", "price history",

  "get quote for", "what''s ETH trading at", "show me top coins", or "track my watchlist".

  '
allowed-tools: Read, Write, Edit, Grep, Glob, Bash(python:*)
version: 1.27.0
author: Jeremy Longshore <[email protected]>
license: MIT
tags:
- crypto
- monitoring
- tracking-crypto
compatibility: Designed for Claude Code
---
# Tracking Crypto Prices

## Contents

[Overview](#overview) | [Prerequisites](#prerequisites) | [Instructions](#instructions) | [Output](#output) | [Error Handling](#error-handling) | [Examples](#examples) | [Resources](#resources)

## Overview

Foundation skill providing real-time and historical cryptocurrency price data for 10,000+ coins. This is the data layer for the crypto plugin ecosystem -- 10+ other skills depend on it for price information.

## Prerequisites

1. Install dependencies: `pip install requests pandas yfinance`
2. Optional: `pip install python-dotenv` for API key management
3. Optional: Get free API key from https://www.coingecko.com/en/api for higher rate limits
4. Add API key to `${CLAUDE_SKILL_DIR}/config/settings.yaml` or set `COINGECKO_API_KEY` env var

## Instructions

1. Check current prices for one or more symbols:

   ```bash
   python ${CLAUDE_SKILL_DIR}/scripts/price_tracker.py --symbol BTC
   python ${CLAUDE_SKILL_DIR}/scripts/price_tracker.py --symbols BTC,ETH,SOL
   ```

2. Use watchlists to scan predefined groups (available: `top10`, `defi`, `layer2`, `stablecoins`, `memecoins`):

   ```bash
   python ${CLAUDE_SKILL_DIR}/scripts/price_tracker.py --watchlist top10     # Top 10 by market cap
   python ${CLAUDE_SKILL_DIR}/scripts/price_tracker.py --watchlist defi      # DeFi tokens
   python ${CLAUDE_SKILL_DIR}/scripts/price_tracker.py --watchlist layer2    # Layer 2 tokens
   ```

3. Fetch historical data by period or custom date range:

   ```bash
   python ${CLAUDE_SKILL_DIR}/scripts/price_tracker.py --symbol BTC --period 30d
   python ${CLAUDE_SKILL_DIR}/scripts/price_tracker.py --symbol BTC --period 90d --output csv
   python ${CLAUDE_SKILL_DIR}/scripts/price_tracker.py --symbol ETH --start 2024-01-01 --end 2024-12-31  # 2024 full year
   ```

4. Configure settings by editing `${CLAUDE_SKILL_DIR}/config/settings.yaml` to customize cache TTLs, default currency, and custom watchlists. See `references/implementation.md` for the full configuration reference.

## Output

- **Table** (default): Symbol, price, 24h change, volume, market cap in formatted columns
- **JSON** (`--format json`): Machine-readable with prices array and metadata
- **CSV** (`--output csv`): OHLCV historical data export to `${CLAUDE_SKILL_DIR}/data/`

See `${CLAUDE_SKILL_DIR}/references/implementation.md` for detailed output format examples.

## Error Handling

| Error | Cause | Solution |
|-------|-------|----------|
| `Unknown symbol: XYZ` | Invalid ticker | Check spelling, use `--list` to search |
| `Rate limit exceeded` | Too many API calls | Wait 60s, or add API key for higher limits |
| `Network error` | No internet | Check connection; cached data used automatically |
| `Cache stale` | Data older than TTL | Shown with warning, refreshes on next call |

The skill auto-manages rate limits: cache first, exponential backoff, yfinance fallback, stale cache as last resort.

## Examples

**Quick price check:**

```bash
python ${CLAUDE_SKILL_DIR}/scripts/price_tracker.py --symbol BTC
# Output: BTC (Bitcoin) $97,234.56 USD +2.34% (24h) | Vol: $28.5B | MCap: $1.92T
```

**Watchlist scan:**

```bash
python ${CLAUDE_SKILL_DIR}/scripts/price_tracker.py --watchlist top10
```

**Historical export:**

```bash
python ${CLAUDE_SKILL_DIR}/scripts/price_tracker.py --symbol ETH --period 90d --output csv
# Creates: ${CLAUDE_SKILL_DIR}/data/ETH_90d_[date].csv
```

## Resources

- `${CLAUDE_SKILL_DIR}/references/implementation.md` - Output formats, full config, integration guide, file map
- [CoinGecko API](https://www.coingecko.com/en/api) - Primary data source
- [yfinance](https://github.com/ranaroussi/yfinance) - Fallback for historical data
05

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
declared (1 observation(s))
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (1)

INFOPrompt injection · prompt.persistence · CWE-94, CWE-1427
references/examples.md:339
# Add to crontab (crontab -e)
Why it matters. instructs the agent to persist itself in the user's environment

Gates applied: no_behavioural_pass.

Audited 2026-10-08 · audit v0.4.1 · source sha 4f83675ca38afull audit observations/trust-audit/skill/jeremylongshore__tracking-crypto-prices.json · Report an issue / request a re-scan
06

Audit history

Every audit this skill has had.

DateSourceVerdictGradeScoreChange
2026-10-084f83675ca38aSAFEB89first audit
07

Questions

What does the Tracking Crypto Prices skill do?

Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.

Is Tracking Crypto Prices safe to install?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.

What can Tracking Crypto Prices access on my machine?

The audit observed that it reaches the network. Each of those is consistent with what it says it does. Secrets in the source: none found.

Which assistants does Tracking Crypto Prices work with?

Its documentation mentions claude-code. That is what the text claims, not a compatibility test we ran.

How current is this page?

The grade is for one exact copy of the source (4f83675ca38a), read on 2026-10-08. The repository is watched, and a new audit runs when it changes — this is the first audit.

Advertisement