How to Use Command A in Claude Code
Command A handles document-based questions, multilingual support, and SQL generation. Its 256,000-token context window suits long source material, while replies are capped at 8,000 tokens.
Prompts to try with Command A in Claude Code
Copy an example into Claude Code, or ask in your own words.
Use Command A at temperature 0 to read this project's database schema and draft a PostgreSQL query for weekly active customers. Explain the joins, define an active customer from the schema, and flag any missing definition before writing SQL.
Use Command A at a low temperature to translate the selected Python function into TypeScript. Preserve error handling and return values, and list any behavior that cannot be translated directly.
Use Command A to explain how authentication works in this repository. Reference file paths and function names for each step, and separate what the code shows from anything you cannot establish.
Use Command A to compare the README with the current implementation. Return a table of outdated statements, supporting code references, and proposed replacement text.
Use Command A to extract configuration requirements from the project's documentation into JSON. Include each setting's name, purpose, documented default, and source path; use null for undocumented defaults and return no Markdown fences.
How to set up Command A in Claude Code
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the hosted server
This adds Spiral to the current project. Add --scope user to use it in every project.
claude mcp add --transport http spiral https://api.spiral.ai/mcp
- Sign in
Start claude, type /mcp, choose spiral and Authenticate. Sign in to Spiral in the browser and click Authorize. No API key.
Use the Spiral skill
- Send Claude Code this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run Command A
One request; the result comes back by polling or a webhook.
curl https://api.spiral.ai/v1/runs \ -H "Authorization: Bearer $SPIRAL_API_KEY" \ -H "Content-Type: application/json" \ -H "Idempotency-Key: $(uuidgen)" \ -d '{ "provider": "openrouter", "model": "cohere/command-a", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Claude Code finds Command A on Spiral, shows the price and runs it.
Command A providers and prices
Spiral runs Command A through OpenRouter. Open a card for today's price, with every fee included.
Up to $0.053363 per run at the default inputs. $3.25 per 1M input tokens, $13.00 per 1M output tokens.
Settings you can ask for
Ask Claude Code for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Seed | a whole number | ||
| Top k | a whole number from 0 | ||
| Top p | 0 to 1 | ||
| Max tokens | 1 to 8192 | The most output tokens to generate. | |
| Temperature | 0 to 2 | ||
| Presence penalty | -2 to 2 | ||
| Frequency penalty | -2 to 2 |
Every API field of Cohere: Command A is on its tool page: open its card above.
What can you do with Command A in Claude Code?
Turn project code, schemas, and documentation into SQL drafts, translated functions, and source-based explanations. Command A is useful for focused code work when you provide the relevant files and spell out the expected behavior.
Employee policy answers
Answer questions from supplied HR policies, separating rules by office location and referencing the relevant passage.
Financial report briefs
Summarize long financial reports into a short brief with reported figures, reporting periods, and source references.
SQL query drafting
Turn a reporting question and database schema into a draft SQL query, with assumptions about joins and date ranges stated explicitly.
Code translation
Rewrite an existing function in another programming language, preserving its behavior and identifying differences that need review.
Multilingual customer replies
Draft answers in French, Spanish, German, or Japanese using supplied product information and support policies.
Knowledge base answers
Combine retrieved help articles into a direct answer with references to the passages that support it.
Support request categorization
Sort incoming requests into defined categories using a few labeled examples, then return a concise result for each request.
Structured text extraction
Extract dates, organizations, owners, and action items from business text into a requested JSON structure, marking missing values explicitly.
More on Command A and Claude Code
Overview
Command A in other agents
Questions about Command A in Claude Code
Can Claude Code use Command A?
Yes. Add Spiral to Claude Code as an MCP server, and Claude Code can find and run Command A like any built-in tool.
How much does Command A cost in Claude Code?
Up to $0.053363 per run at the default inputs. $3.25 per 1M input tokens, $13.00 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Claude Code plan is separate.
Do I need an OpenRouter account to use Command A in Claude Code?
No. Spiral runs Command A on its own OpenRouter account. You sign in to Spiral once and never paste a key.
How long does it take to set up Command A in Claude Code?
About two minutes: add the hosted server, then sign in.
Does Claude Code wait while Command A runs?
Command A runs in the background. Claude Code starts the run, checks on it and gives you the text, json when it's ready.
What is Command A good at?
Command A is useful for answering questions from supplied documents, summarizing business information, multilingual text work, and SQL generation. Give it the relevant source material and specify the result you need.
How much text can Command A handle?
Cohere documents a 256,000-token context window and a maximum output of 8,000 tokens. Plan long writing tasks as separate sections rather than requesting a book-length response in one pass.
Which languages does Command A support?
Command A supports 23 languages, including English, French, Spanish, Italian, German, Portuguese, Japanese, and Korean. State the desired response language explicitly when working across languages.
Is Command A useful for coding?
SQL generation and code translation are documented uses. Cohere recommends a low temperature for code generation; include the database schema, target language, and expected behavior in your request.
Why does Command A add introductions and code fences?
Command A is conversational and verbose by default. Use a system instruction that asks for only the requested answer, with no introduction, follow-up question, or Markdown code fences.
Start using Command A in Claude Code
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Claude Code:
set up https://spiral.ai/SKILL.md


