Skip to main content
command CX Codex

cook — Claude Code command: what it does, how to install

cook dispatches seven parallel sub-agent workflows covering crypto research, LLM engineering trends, and specialized agent creation.

no license ★ 3,990 updated 2026-03-04

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
.claude/commands/cook.md
Open on GitHub

What cook does

The command delegates seven independent assignments simultaneously. Two tasks focus on digital assets: evaluating DOGE sentiment alongside technical indicators, and pulling broad cryptocurrency market figures. Another task explores modern autonomous agent frameworks and engineering patterns for language models.

The remaining four assignments rely on meta-agent to configure specialized tooling. It designs dedicated assistants for security audits around OWASP top 10 rules, bottleneck discovery, automated documentation, and test gap analysis.

Executing this command requires the referenced sub-agents to exist in your environment. If meta-agent or the market analytical assistants are missing, the delegated tasks will fail.

What it helps with

  • pull market metrics and sentiment indicators for DOGE
  • study recent developments in AI agent frameworks
  • build a sub-agent to audit code for OWASP top 10 flaws
  • generate a helper agent that inspects unit test coverage

Example prompts for the agent

  • /cook
  • Run the parallel agent workflow using /cook

How to install cook

Manually: put the files in place

.claude/commands/cook.md

Call it with /cook. For all projects use ~/.claude/commands/

Questions about cook

How do I install cook in Claude Code?

Add the file .claude/commands/cook.md inside your repository directory with the command prompt text.

What does cook do?

It triggers seven concurrent tasks across sub-agents, handling cryptocurrency research, LLM tooling investigations, and automated agent design.

Does cook require existing sub-agents?

Yes, your setup must define the referenced agents like meta-agent and the crypto research helpers, or the tasks will halt with errors.

Similar slash commands

All slash commands for Agent setup: memory, context, orchestration →

From the same set25

The whole set →
build build reads a plan file, applies it to your codebase and prints the report section from that plan. Useful once the plan is written and only the implementation is left. CX Codex +1 ★ 3,990repo stars prime prime prepares agent context at the start of a session by inspecting project structure, reading core docs, and summarizing findings. CX Codex +1 ★ 3,990repo stars cook_research_only The cook_research_only command runs seven research tasks in parallel: five crypto reviews, market data collection, and a search for AI agent and LLM engineering practices. CX Codex +1 ★ 3,990repo stars hello-world-agent hello-world-agent — a Claude Code subagent that greets the user and asks what they need. It triggers on "hi claude", "hi cc", or "hi claude code". CX Codex ★ 3,990repo stars prime_tts The prime_tts command checks the repository’s file structure and reads README.md to prepare a short project overview for a new session. It then runs the tts summary agent. CX Codex +1 ★ 3,990repo stars crypto_news_scanner_agent_prompt crypto_news_scanner_agent_prompt — a slash command that pulls recent crypto headlines and returns the 5 biggest with sources. Handy for a quick market check. CX Codex +1 ★ 3,990repo stars crypto_price_check_agent_prompt crypto_price_check_agent_prompt fetches current cryptocurrency prices in USD directly inside Claude Code. Checks Bitcoin if no token ticker is provided. CX Codex +1 ★ 3,990repo stars crypto_movers_agent_prompt crypto_movers_agent_prompt finds the biggest percentage gainers and losers among cryptocurrencies in the top 100 by market cap. Pass a timeframe such as 7d to change the period. CX Codex +1 ★ 3,990repo stars

Project sponsors

Companies that keep this analytics open