How to Use GPT Astra in Claude Code
GPT Astra suits complex coding, research, and document work with several requirements to track. Give it a clear deliverable and verification criteria so it can carry the work through to a reviewable result.
Prompts to try with GPT Astra in Claude Code
Copy an example into Claude Code, or ask in your own words.
Use GPT Astra with high reasoning effort to investigate the failing checkout tests in this repository. Reproduce the failure, trace its cause, make a focused fix, and report the tests run and any remaining failures.
Use GPT Astra to review this project's database migration scripts. Produce a migration plan covering compatibility with the current application, rollback conditions, and concrete checks before and after migration.
Use GPT Astra to refactor the duplicated validation code in this project. Preserve public behavior, follow the existing conventions, and verify the affected paths with the project's relevant tests.
Use GPT Astra to implement keyboard navigation for this project's existing settings dialog. Preserve its appearance and verify focus order, Escape behavior, and focus restoration.
Use GPT Astra to review the current branch for correctness defects. Trace each finding through the relevant files and return only actionable findings with a reproduction or a precise explanation of the failing path.
How to set up GPT Astra 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 GPT Astra
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": "openai", "model": "~openai/gpt-astra-latest", "input": { "messages": [ { "role": "user", "content": "Hello!" } ] } }'
Then paste one of the prompts above: Claude Code finds GPT Astra on Spiral, shows the price and runs it.
GPT Astra providers and prices
Spiral runs GPT Astra through OpenAI. Open a card for today's price, with every fee included.
Up to $0.213447 per run at the default inputs. $10.40 per 1M input tokens, $0.52 per 1M cached input tokens, $13.00 per 1M cache write tokens, $52.00 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 | ||
| Max tokens | 16 to 128000 | The most output tokens to generate. On a reasoning model the reasoning tokens count toward it: a cap too low for the effort can end with no answer (finish_reason length). | |
| Reasoning effort | low, medium, high, or xhigh | How much the model reasons. | |
| Parallel tool calls | on or off |
Every API field of GPT Astra Latest is on its tool page: open its card above.
What can you do with GPT Astra in Claude Code?
GPT Astra can turn a difficult bug or a change spanning several files into a tested implementation. Give it the relevant project context, coding conventions, and acceptance checks.
Debug a failure across several files
Have GPT Astra trace a reported failure through the relevant code, propose a focused fix, and verify it against a reproducible test.
Plan a database migration
Ask GPT Astra to turn schema changes and operational constraints into a migration plan with compatibility checks, rollback conditions, and unresolved decisions.
Write a research decision brief
Give GPT Astra source material and a concrete decision. Request a brief that connects supporting evidence, disagreements, and information still needed.
Draft a report in an established format
Supply a report template, source text, and audience. Ask GPT Astra to preserve the section order and style while filling gaps only where the evidence supports them.
Develop a presentation narrative
Use GPT Astra to turn research notes into a slide-by-slide argument, with a clear takeaway and supporting evidence for each slide.
Review a business approval process
Ask GPT Astra to check written approval rules against normal cases and exceptions. Request a table of expected outcomes for human review.
Extract evidence into structured records
Have GPT Astra convert supplied text into JSON records with evidence excerpts and explicit missing values. Validate the records against the schema and your business rules.
More on GPT Astra and Claude Code
Overview
GPT Astra in other agents
More Claude Code guides
Questions about GPT Astra in Claude Code
Can Claude Code use GPT Astra?
Yes. Add Spiral to Claude Code as an MCP server, and Claude Code can find and run GPT Astra like any built-in tool.
How much does GPT Astra cost in Claude Code?
Up to $0.26681 per run at the default inputs. $13.00 per 1M input tokens, $1.30 per 1M cached input tokens, $16.25 per 1M cache write tokens, $65.00 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 OpenAI account to use GPT Astra in Claude Code?
No. Spiral runs GPT Astra on its own OpenAI account. You sign in to Spiral once and never paste a key.
How long does it take to set up GPT Astra in Claude Code?
About two minutes: add the hosted server, then sign in.
Does Claude Code wait while GPT Astra runs?
GPT Astra runs in the background. Claude Code starts the run, checks on it and gives you the text, json when it's ready.
What is GPT Astra good at?
GPT Astra suits complex coding, research, and document creation. Use it when the task requires connecting evidence, tracking requirements, and producing a finished deliverable.
What are Astra's context and output limits?
OpenAI documents a 1,050,000-token context window and a maximum of 128,000 output tokens for GPT-6 Astra. Internal reasoning also consumes the output budget, so that maximum does not mean 128,000 tokens of visible text.
How should I prompt GPT Astra?
State the deliverable, constraints, desired format, and checks that define success. Use direct instructions; you do not need to ask it to reveal its internal reasoning.
When should I adjust reasoning effort?
Use lower effort for straightforward follow-ups where speed matters. For difficult work, test higher effort against clear acceptance criteria and leave enough output space for both reasoning and the answer.
Why does GPT Astra sometimes ask a question instead of finishing?
Astra may request clarification when missing information could change the result. Tell it which assumptions it may make, which decisions require your input, and what it should finish before stopping.
Start using GPT Astra 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


