A workflow for creating new parts of a crypto-trading system from a plain-language request. It can plan an MCP server, agent, or skill, then research the needed APIs and existing project patterns.

Use it to request components such as a DeFi data tracker, macro-analysis agent, multi-coin comparison workflow, or portfolio alert system.

It turns a broad request into a defined component type and a documented implementation plan. This helps avoid building a component without checking available data sources or project conventions.

create — Skill for Claude Code by hugoguerrap

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 hugoguerrap/crypto-claude-desk --skill create

Clone the repo

git clone --depth 1 https://github.com/hugoguerrap/crypto-claude-desk

Made for: Claude Code.

Or install crypto-trading-desk, the plugin that ships this one along with the rest of its 8 skills, 7 agents, 1 hook.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/hugoguerrap/crypto-claude-desk/create/github.svg)](https://agentmods.dev/skills/hugoguerrap/crypto-claude-desk/create)

Your own site

<a href="https://agentmods.dev/skills/hugoguerrap/crypto-claude-desk/create"><img src="https://agentmods.dev/badge/skills/hugoguerrap/crypto-claude-desk/create/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/hugoguerrap/crypto-claude-desk/create"><img src="https://agentmods.dev/badge/skills/hugoguerrap/crypto-claude-desk/create.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 947 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00033	$0.00947
Opus 5	$0.00016	$0.00474
Sonnet 5	$0.00007	$0.00189
Haiku 4.5	$0.00003	$0.00095

Measured 9d ago against content hash ef758639647d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

create 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 9d 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/create/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create New Component

Extend the crypto trading desk with a new component based on the user's natural language description: $ARGUMENTS

Workflow

Step 1: Parse Request

Determine what the user wants to create:

MCP server — if the request involves new data sources, APIs, or tools (e.g., "on-chain analytics", "DeFi tracker", "social media monitor")
Agent — if the request involves a new specialist role (e.g., "macro analyst", "DeFi strategist", "on-chain detective")
Skill — if the request involves a new workflow or command (e.g., "multi-coin comparison", "rebalance portfolio", "alert system")

If unclear, ask the user what type of component they want.

Step 2: Research

Delegate to system-builder agent: "Research what's needed to create: $ARGUMENTS. Use WebSearch to find relevant public APIs (prefer no-API-key-required). Use WebFetch to read API documentation. Read existing components in the project to understand patterns — read at least 2 files from the relevant directory (mcp-servers/, agents/, or skills/). Read mcp-servers/validators.py for reusable validation. Write a research summary to data/create/{name}-research.md with: APIs found, rate limits, data available, recommended approach."

Step 3: Generate

After research completes, delegate to system-builder agent: "Based on the research in data/create/{name}-research.md, generate a new {type} for: $ARGUMENTS. Follow the exact patterns from existing files. Write the component to the correct location:

MCP server → mcp-servers/{name}.py
Agent → agents/{name}.md
Skill → skills/{name}/SKILL.md Write a creation summary to data/create/{name}-summary.md."

Step 3b: Generate Tests (MCP servers only)

If the component is an MCP server, delegate to system-builder agent: "Generate a test file for the new MCP server mcp-servers/{name}.py. Read tests/helpers.py to understand the call_tool() helper. Read at least 2 existing test files (e.g., tests/test_crypto_data.py, tests/test_crypto_exchange.py) to understand the testing pattern:

Import with sys.path.insert(0, str(Path(__file__).resolve().parent.parent / 'mcp-servers'))
Use from helpers import call_tool wrapper for FastMCP tools
Mock ALL external API calls (HTTP, CCXT, etc.) — tests must run offline
One test class per tool, with at least: test_success and test_error_handling
Assert result['status'] == 'success' on happy path
Assert result['status'] == 'error' on failure path Write the test to tests/test_{name}.py."

Read the full file on GitHub · 72 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.

9d ago First seen · 72 lines · 0 tokens per session scan A ef758639647d

Subscribe to this mod's changes

create is a skill published in the GitHub repository hugoguerrap/crypto-claude-desk (33 stars, last pushed 17d ago), licensed MIT. It adds 33 tokens to every session and 947 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.

Building agents Claude Code ai-agents anthropic claude-code-plugin crypto-trading cryptocurrency

docs-drift

Documentation-drift audit for this plugin monorepo. Audit either each scoped plugin's unreleased changelog claims or its latest shipped release from the previous reachable plugin-name--v tag, then verify that plugin READMEs, docs, CLAUDE.md or AGENTS.md files, and root documentation tell the truth for the matching…

gtapps/claude-code-hermit · 170 tokens

cco-tools

Show what tools actually cost in tokens — learned per-tool averages from observed results, replacing the hardcoded MCP/Agent guesses.

egorfedorov/claude-context-optimizer · 27 tokens

github-pr-creation

Creates GitHub Pull Requests with automated validation and task tracking. Use when user wants to create PR, open pull request, submit for review, or check if ready for PR. Analyzes commits, validates task completion, generates Conventional Commits title and description, suggests labels. NOTE - for merging existing…

fvadicamo/dev-agent-skills · 75 tokens

create