How to Use Claude Opus 4.5 in Muse Code
Claude Opus 4.5 suits difficult software engineering and detailed research. Its 200,000-token context window and maximum 64,000-token output give it room for large code reviews and substantial reports.
Prompts to try with Claude Opus 4.5 in Muse Code
Copy an example into Muse Code, or ask in your own words.
Use Claude Opus 4.5 to investigate the failing tests in this repository. Read the affected implementation, identify the root cause, make the smallest complete fix, and run the relevant tests without refactoring unrelated code.
Use Claude Opus 4.5 to review the current diff for correctness. Trace affected callers, rank concrete findings by impact, and cite the relevant file and line for each finding.
Use Claude Opus 4.5 to plan the migration described in this project's issue. Inspect the dependencies, identify behavior that must stay consistent, and propose small steps with a verification check for each.
Use Claude Opus 4.5 to trace how this project handles an incoming request through validation, business logic, and persistence. Cite the implementation and explain where failures are handled.
Use Claude Opus 4.5 to implement the acceptance criteria in the project's task description. Follow existing conventions, avoid new abstractions unless required, and report the checks you actually ran.
How to set up Claude Opus 4.5 in Muse Code
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Install Muse Code
curl -fsSL https://dev.meta.ai/install.sh | bash
- Ask Muse to add the server
Start muse and ask:
Add the Spiral MCP server at https://api.spiral.ai/mcp
- Sign in
In your terminal, run:
muse mcp login spiral
Use the Spiral skill
- Send Muse 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 Claude Opus 4.5
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-4.5", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Muse Code finds Claude Opus 4.5 on Spiral, shows the price and runs it.
Claude Opus 4.5 providers and prices
Spiral runs Claude Opus 4.5 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 Muse Code for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Top p | 0 to 1 | ||
| Max tokens | 1 to 64000 | 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). | |
| Temperature | 0 to 1 | ||
| Parallel tool calls | on or off |
Every API field of Claude Opus 4.5 is on its tool page: open its card above.
What can you do with Claude Opus 4.5 in Muse Code?
Claude Opus 4.5 can help turn a difficult bug or broad code change into an implementation you can review. Use project context to trace dependencies, then specify a narrow scope to limit unnecessary abstractions.
Investigate bugs across components
Use Claude Opus 4.5 to trace a failure through related code, explain the cause, and propose a focused fix with a regression check.
Review substantial code changes
Ask Claude Opus 4.5 to examine a change for correctness, identify affected behavior, and rank findings by impact.
Plan a code migration
Have Claude Opus 4.5 map dependencies, divide a migration into testable steps, and define checks for preserving existing behavior.
Reconcile conflicting research
Give Claude Opus 4.5 source material and ask for an evidence table that separates agreement, contradictions, and unanswered questions.
Explain spreadsheet discrepancies
Ask Claude Opus 4.5 to examine supplied tables and formulas, trace inconsistent totals, and explain which assumptions need checking.
Draft an evidence-based presentation
Use Claude Opus 4.5 to turn research and business results into slide headlines, supporting evidence, and speaker notes.
Adapt research for another language
Ask Claude Opus 4.5 to summarize supplied findings in a named language while preserving technical terms, numbers, and source references.
More on Claude Opus 4.5 and Muse Code
Claude Opus 4.5 in other agents
Questions about Claude Opus 4.5 in Muse Code
Can Muse Code use Claude Opus 4.5?
Yes. Add Spiral to Muse Code as an MCP server, and Muse Code can find and run Claude Opus 4.5 like any built-in tool.
How much does Claude Opus 4.5 cost in Muse Code?
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 Muse Code plan is separate.
Do I need an Anthropic account to use Claude Opus 4.5 in Muse Code?
No. Spiral runs Claude Opus 4.5 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 4.5 in Muse Code?
About two minutes: install Muse Code, then ask Muse to add the server, then sign in.
Does Muse Code wait while Claude Opus 4.5 runs?
Claude Opus 4.5 runs in the background. Muse Code starts the run, checks on it and gives you the text, json when it's ready.
What is Claude Opus 4.5 good at?
Difficult software engineering, deep research, and analysis involving spreadsheets or presentations are documented strengths. Try it for a bug that crosses several components or a report that must reconcile conflicting evidence.
How much context and output can Claude Opus 4.5 handle?
It has a 200,000-token context window and can generate up to 64,000 output tokens. Treat these as token limits rather than fixed page counts.
Does Claude Opus 4.5 generate images or video?
Its output is text. Use it to write code, reports, presentation copy, or production briefs.
What limitations should I plan around?
Anthropic documents a tendency to overengineer code, so specify the exact scope and ask for minimal changes. Its reliable knowledge cutoff is May 2025; supply current evidence for questions about later events.
How should I prompt Claude Opus 4.5 for document analysis?
Ask it to extract relevant passages before drawing conclusions. Request a source reference beside each conclusion so you can check the reasoning against the supplied material.
Start using Claude Opus 4.5 in Muse Code
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Muse Code:
set up https://spiral.ai/SKILL.md


