How to Use Claude Opus 4.8 in Google Antigravity
Claude Opus 4.8 suits complex coding, document analysis, and tasks that require several steps. Compared with Claude Opus 4.7, Anthropic reports it is about four times less likely to leave flaws in its own code unflagged.
Prompts to try with Claude Opus 4.8 in Google Antigravity
Copy an example into Google Antigravity, or ask in your own words.
Use Claude Opus 4.8 with extra high reasoning effort to investigate the failing tests in this project. Trace the cause, make the smallest justified fix, and report which checks passed.
Use Claude Opus 4.8 to review the current diff for bugs that could cause incorrect behavior or test failures. Include the affected location, evidence, severity, and confidence for every finding.
Use Claude Opus 4.8 with extra high reasoning effort to inspect the authentication flow and plan a refactor. Preserve existing behavior, identify dependencies, and define acceptance checks before editing.
Use Claude Opus 4.8 to compare this project's implementation with its written requirements. Apply every requirement to all relevant modules and report missing behavior with supporting code locations.
Use Claude Opus 4.8 to turn the project's architecture notes into a technical decision memo. Compare the documented approaches, state unresolved questions, and keep the memo under 800 words.
How to set up Claude Opus 4.8 in Google Antigravity
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Open the MCP config
* Antigravity App: click Customizations, then Installed. In the MCP Servers section, click Copy Config File Path and open that file. * Antigravity IDE: click … at the top of the agent side panel, select MCP Servers, then Manage MCP Servers › View raw config. * Antigravity CLI: edit ~/.gemini/config/mcp_config.json.
- Add the server
Add Spiral under mcpServers:
{ "mcpServers": { "spiral": { "serverUrl": "https://api.spiral.ai/mcp" } } } - Sign in
In the Antigravity App, open Customizations › Installed. Under MCP Servers, click Authenticate next to Spiral. Sign in to Spiral, pick the organization and click Authorize. Copy the authorization code the browser shows, paste it into Enter authorization code and click Submit. No API key.
Use the Spiral skill
- Send Google Antigravity 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 Claude Opus 4.8
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": "anthropic", "model": "anthropic/claude-opus-4.8", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Google Antigravity finds Claude Opus 4.8 on Spiral, shows the price and runs it.
Claude Opus 4.8 providers and prices
Spiral runs Claude Opus 4.8 through Anthropic. Open a card for today's price, with every fee included.
Up to $0.133575 per run at the default inputs. $6.50 per 1M input tokens, $0.65 per 1M cached input tokens, $8.125 per 1M cache write tokens, $13.00 per 1M 1-hour cache write tokens, $32.50 per 1M output tokens; for a prompt above 200,000 tokens, $13.00 per 1M input tokens, $1.30 per 1M cached input tokens, $16.25 per 1M cache write tokens, $26.00 per 1M 1-hour cache write tokens, $48.75 per 1M output tokens.
Settings you can ask for
Ask Google Antigravity for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Max tokens | 1 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 | none, minimal, low, medium, high, xhigh, or max | none | How much the model reasons. |
| Parallel tool calls | on or off |
Every API field of Claude Opus 4.8 is on its tool page: open its card above.
What can you do with Claude Opus 4.8 in Google Antigravity?
Claude Opus 4.8 can help trace bugs across a project, review changes, and carry a migration through several steps. Give it concrete acceptance criteria and ask it to distinguish code changes from verified results.
Investigate a difficult bug
Trace a failure across related functions, identify the cause, and propose a fix with a regression check.
Review a code change
Look for incorrect behavior, missing error handling, and test failures. Request evidence, severity, and confidence for each finding.
Plan a code migration
Compare existing behavior with the target requirements, map dependencies, and produce an ordered implementation and validation plan.
Compare competing proposals
Evaluate supplied proposals against the same criteria and produce a decision table that exposes missing information.
Extract records from text
Turn meeting notes or business correspondence into consistently formatted records with explicit rules for missing values.
Build a research brief
Combine supplied source text into a focused brief that separates agreement, conflicting evidence, and unanswered questions.
Draft a technical decision memo
Turn requirements, constraints, and proposed approaches into a memo covering tradeoffs and the evidence needed to choose.
Summarize recurring operational issues
Analyze a supplied batch of incident summaries or support conversations and organize recurring problems for review.
More on Claude Opus 4.8 and Google Antigravity
Claude Opus 4.8 in other agents
More Google Antigravity guides
Questions about Claude Opus 4.8 in Google Antigravity
Can Google Antigravity use Claude Opus 4.8?
Yes. Add Spiral to Google Antigravity as an MCP server, and Google Antigravity can find and run Claude Opus 4.8 like any built-in tool.
How much does Claude Opus 4.8 cost in Google Antigravity?
Up to $0.133575 per run at the default inputs. $6.50 per 1M input tokens, $0.65 per 1M cached input tokens, $8.125 per 1M cache write tokens, $13.00 per 1M 1-hour cache write tokens, $32.50 per 1M output tokens; for a prompt above 200,000 tokens, $13.00 per 1M input tokens, $1.30 per 1M cached input tokens, $16.25 per 1M cache write tokens, $26.00 per 1M 1-hour cache write tokens, $48.75 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Google Antigravity plan is separate.
Do I need an Anthropic account to use Claude Opus 4.8 in Google Antigravity?
No. Spiral runs Claude Opus 4.8 on its own Anthropic account. You sign in to Spiral once and never paste a key.
How long does it take to set up Claude Opus 4.8 in Google Antigravity?
About two minutes: open the MCP config, then add the server, then sign in.
Does Google Antigravity wait while Claude Opus 4.8 runs?
Claude Opus 4.8 runs in the background. Google Antigravity starts the run, checks on it and gives you the text, json when it's ready.
What is Claude Opus 4.8 good at?
Use it for complex coding, bug investigation, document analysis, and work that takes several steps. It also suits extracting consistent records from text when you define the expected output precisely.
How much text can Claude Opus 4.8 handle?
Its context window holds up to 1 million tokens, including conversation history and generated output, with a standard output limit of 128,000 tokens. Keep the supplied material relevant because accuracy and recall can decline as context grows.
Which reasoning effort should I use?
Anthropic recommends extra high effort for coding and tasks involving multiple agent actions, and high effort for other demanding analysis. Try lower effort on narrowly defined tasks and check whether the results still meet your requirements.
How should I prompt Claude Opus 4.8?
State the task, scope, constraints, and exact output you want. Say whether each instruction applies to every record or section because Claude Opus 4.8 follows wording literally.
Why might Claude Opus 4.8 omit bugs during a code review?
Instructions such as “only report important issues” can make it filter out bugs it considers below that threshold. Define what counts as a reportable bug, or request findings with severity and confidence so you can assess them afterward.
Start using Claude Opus 4.8 in Google Antigravity
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Google Antigravity:
set up https://spiral.ai/SKILL.md


