How to Use Claude Opus 5.5 in OpenClaw
Claude Opus 5.5 is built for long coding tasks, large refactors, and detailed knowledge work. Compared with Claude Opus 5, it generates output more than 30% faster in Anthropic’s tests.
Prompts to try with Claude Opus 5.5 in OpenClaw
Copy an example into OpenClaw, or ask in your own words.
Every Monday, use Claude Opus 5.5 to review the past week's official release notes for PostgreSQL. Produce a dated brief of relevant changes with source links, and say explicitly when no relevant release was found.
Each weekday, use Claude Opus 5.5 to review newly available material from the connected research sources. Summarize evidence that changes our existing conclusions, cite the original passages, and list unresolved questions.
Every Friday, use Claude Opus 5.5 to compare the week's connected project updates. Report conflicting deadlines, missing owners, and unresolved dependencies with supporting passages; finish only after checking all three categories.
Each month, use Claude Opus 5.5 to check the connected operating report for inconsistent totals and assumptions. Show the calculation behind each finding, and mark unavailable evidence instead of estimating it.
Every morning, use Claude Opus 5.5 to prepare a 400-word brief from new items in the connected industry sources. Include only supported developments, link each source, and check every claim before completing the report.
How to set up Claude Opus 5.5 in OpenClaw
Pick the way that suits you. Each takes about two minutes.
Use the Spiral skill
- Send OpenClaw 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 Spiral's MCP server
- Add the server
On the machine that runs OpenClaw's Gateway:
openclaw mcp add spiral \ --url https://api.spiral.ai/mcp \ --transport streamable-http \ --auth oauth
- Sign in
In Settings › MCP, select Sign in on the Spiral server, sign in to Spiral and click Authorize. No API key.
openclaw mcp login spiral
- Reload and check
A running Gateway may keep its old tool list: restart it, or Save & Publish in the Control UI.
openclaw mcp reload openclaw mcp doctor spiral --probe
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 5.5
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-5.5", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: OpenClaw finds Claude Opus 5.5 on Spiral, shows the price and runs it.
Claude Opus 5.5 providers and prices
Spiral runs Claude Opus 5.5 through Anthropic. Open a card for today's price, with every fee included.
Up to $0.10686 per run at the default inputs. $5.20 per 1M input tokens, $0.26 per 1M cached input tokens, $6.50 per 1M cache write tokens, $10.40 per 1M 1-hour cache write tokens, $26.00 per 1M output tokens; for a prompt above 200,000 tokens, $10.40 per 1M input tokens, $0.52 per 1M cached input tokens, $13.00 per 1M cache write tokens, $20.80 per 1M 1-hour cache write tokens, $39.00 per 1M output tokens.
Settings you can ask for
Ask OpenClaw 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 | low, medium, high, xhigh, or max | medium | How much the model reasons. |
| Parallel tool calls | on or off |
Every API field of Claude Opus 5.5 is on its tool page: open its card above.
What can you do with Claude Opus 5.5 in OpenClaw?
Produce recurring research briefs and consistency checks with Claude Opus 5.5. Define what each report must contain and verify those requirements before marking a scheduled task complete.
Migrate a large codebase
Use Claude Opus 5.5 to move deprecated interfaces to their replacements, update affected tests, and report any remaining blockers against a migration checklist.
Refactor across modules
Ask Claude Opus 5.5 to trace dependencies, simplify duplicated logic, and verify that the affected behavior still passes its tests.
Review a complicated change
Have Claude Opus 5.5 examine a patch and its surrounding code, then report reproducible defects with evidence and a suggested test.
Prepare a research brief
Give Claude Opus 5.5 the source material and a specific decision to support. Request a concise brief with quotations for key claims and a list of unresolved questions.
Check a financial analysis
Ask Claude Opus 5.5 to inspect supplied calculations, identify inconsistent assumptions, and explain how each proposed correction changes the result.
Reconcile planning records
Use Claude Opus 5.5 to compare lengthy planning material, flag conflicting commitments, and produce a decision log with evidence for each entry.
More on Claude Opus 5.5 and OpenClaw
Claude Opus 5.5 in other agents
Questions about Claude Opus 5.5 in OpenClaw
Can OpenClaw use Claude Opus 5.5?
Yes. Add Spiral to OpenClaw as an MCP server, and OpenClaw can find and run Claude Opus 5.5 like any built-in tool.
How much does Claude Opus 5.5 cost in OpenClaw?
Up to $0.10686 per run at the default inputs. $5.20 per 1M input tokens, $0.26 per 1M cached input tokens, $6.50 per 1M cache write tokens, $10.40 per 1M 1-hour cache write tokens, $26.00 per 1M output tokens; for a prompt above 200,000 tokens, $10.40 per 1M input tokens, $0.52 per 1M cached input tokens, $13.00 per 1M cache write tokens, $20.80 per 1M 1-hour cache write tokens, $39.00 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your OpenClaw plan is separate.
Do I need an Anthropic account to use Claude Opus 5.5 in OpenClaw?
No. Spiral runs Claude Opus 5.5 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 5.5 in OpenClaw?
About two minutes: add the server, then sign in, then reload and check.
Does OpenClaw wait while Claude Opus 5.5 runs?
Claude Opus 5.5 runs in the background. OpenClaw starts the run, checks on it and gives you the text, json when it's ready.
What is Claude Opus 5.5 best suited for?
Use it for work with several dependent steps, such as a large refactor, a code migration, or a detailed analysis. Give it a concrete deliverable and a clear completion checklist.
How much text can Claude Opus 5.5 handle?
It has a 1 million token context window and supports up to 128,000 output tokens in a standard response. Thinking also uses the output budget, so the full allowance is not available for the visible answer.
Does higher effort always produce a better result?
Test effort settings on your actual tasks before choosing one. For demanding work, leave enough output space for thinking and the answer, then compare correctness and completeness.
How should I prompt Claude Opus 5.5?
State the deliverable, constraints, and completion criteria explicitly. Include an example when the answer must follow a particular format or writing style.
Can I trust every figure or citation it produces?
Check important claims against their sources. Ask for supporting quotations, and tell it to mark missing evidence instead of filling gaps.
Start using Claude Opus 5.5 in OpenClaw
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into OpenClaw:
set up https://spiral.ai/SKILL.md


