Spiral gives your agent every tool with one account. Browse the tools →

opencode · LLMReleased 2026-09-02

How to Use Muse Spark 1.3 Contributor in opencode

Muse Spark 1.3 Contributor fits coding experiments and extended tasks with conflicting information. Unlike Muse Spark 1.3, it does not support Meta's max reasoning mode.

Prompts to try with Muse Spark 1.3 Contributor in opencode

Copy an example into opencode, or ask in your own words.

Use Muse Spark 1.3 Contributor with high reasoning to investigate the failing tests in this project. Trace the failure to its cause, make a focused fix, and run the relevant regression checks.

Muse Spark 1.3 Contributoropencode
Try asking
  • Use Muse Spark 1.3 Contributor to compare this project's README requirements with its implementation. Report missing behavior with file references and propose an ordered repair plan.

  • Use Muse Spark 1.3 Contributor with high reasoning to plan this project's next dependency upgrade. Inspect the manifests and affected code, identify compatibility risks, and define checks for each migration step.

  • Use Muse Spark 1.3 Contributor to refactor the duplicated validation code in this repository. Preserve current behavior, explain conflicting assumptions you find, and verify the affected paths.

  • Use Muse Spark 1.3 Contributor to review the current diff against the issue's acceptance criteria. Prioritize correctness problems and give a concrete reproduction for each finding.

How to set up Muse Spark 1.3 Contributor in opencode

Pick the way that suits you. Each takes about two minutes.

Use Spiral's MCP server

  1. Add the server

    Leave out --global to add Spiral to the current project only. No header and no client ID or secret: opencode registers itself with Spiral.

    opencode mcp add spiral --global --url https://api.spiral.ai/mcp
  2. Sign in

    Your browser opens. Sign in to Spiral, pick the organization and click Authorize, then return to the terminal. No API key. Inside opencode, /mcps starts the same sign-in.

    opencode mcp auth spiral
  3. Check it

    Spiral shows as connected.

    opencode mcp list

Use the Spiral skill

  1. Send opencode this message

    Your agent reads Spiral's skill and sets itself up.

    set up https://spiral.ai/SKILL.md
  2. Sign in or paste a key

    Approve Spiral in the browser, or give the agent a key from the console.

Use the Spiral CLI

  1. 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

  1. Create an API key

    In the console, under API keys.

  2. Run Muse Spark 1.3 Contributor

    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": "meta/muse-spark-1.3-contributor",
        "input": {
          "messages": [
            {
              "role": "system"
            }
          ]
        }
      }'

Then paste one of the prompts above: opencode finds Muse Spark 1.3 Contributor on Spiral, shows the price and runs it.

Muse Spark 1.3 Contributor providers and prices

Spiral runs Muse Spark 1.3 Contributor through OpenRouter. Open a card for today's price, with every fee included.

OpenRouterLLM
Meta: Muse Spark 1.3 Contributor
meta/muse-spark-1.3-contributor

Settings you can ask for

Ask opencode for any of these in your prompt.

SettingAllowed valuesDefaultDescription
Top ka whole number from 0
Top p0 to 1
Max tokens1 to 943718

The most output tokens to generate.

Temperature0 to 2
Reasoning effortminimal, low, medium, high, xhigh, or maxmedium

How much the model reasons.

Repetition penalty0 to 2

Every API field of Meta: Muse Spark 1.3 Contributor is on its tool page: open its card above.

What can you do with Muse Spark 1.3 Contributor in opencode?

Turn a bug report or migration request into a code change checked against explicit requirements. Muse Spark 1.3 Contributor fits extended engineering work where the agent must track constraints across several steps.

Debug a failure across several modules

Trace a reported failure through the relevant code, compare possible causes, and propose a fix with a regression check.

Plan a dependency migration

Turn current behavior and upgrade requirements into an ordered migration plan with compatibility checks and acceptance criteria.

Review code against detailed requirements

Compare an implementation with its specification and identify missing behavior, conflicting requirements, and questions that need an answer.

Reconcile conflicting project updates

Compare dated updates, identify disagreements, and produce a status brief that distinguishes supported conclusions from unresolved questions.

Build a constrained project plan

Work through dependencies, deadlines, and staffing constraints to produce milestones with explicit completion criteria.

Audit progress on an extended task

Compare the original requirements with completed work and report what is finished, what remains, and which constraints have been missed.

Questions about Muse Spark 1.3 Contributor in opencode

Can opencode use Muse Spark 1.3 Contributor?

Yes. Add Spiral to opencode as an MCP server, and opencode can find and run Muse Spark 1.3 Contributor like any built-in tool.

How much does Muse Spark 1.3 Contributor cost in opencode?

Up to $0.00107 per run at the default inputs. $0.13 per 1M input tokens, $0.26 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your opencode plan is separate.

Do I need an OpenRouter account to use Muse Spark 1.3 Contributor in opencode?

No. Spiral runs Muse Spark 1.3 Contributor on its own OpenRouter account. You sign in to Spiral once and never paste a key.

How long does it take to set up Muse Spark 1.3 Contributor in opencode?

About two minutes: add the server, then sign in, then check it.

Does opencode wait while Muse Spark 1.3 Contributor runs?

Muse Spark 1.3 Contributor runs in the background. opencode starts the run, checks on it and gives you the text, json when it's ready.

What is Muse Spark 1.3 Contributor good at?

It fits coding experiments and extended tasks that require keeping track of requirements or reconciling conflicting information. Give it a concrete deliverable and explicit acceptance criteria.

How much context can Muse Spark 1.3 Contributor handle?

Its context window is 1,048,576 tokens. That is a context limit, not a promise that the visible answer can be that long.

How does Contributor differ from standard Muse Spark 1.3?

Contributor mode permits your content to be used to train future Meta models. Meta also documents max reasoning as unavailable for Contributor.

When should I use more reasoning?

Use higher reasoning effort for problems with several dependent steps, such as debugging or planning a migration. Reasoning shares the output budget with the final answer, so leave room for both.

How do I get more focused answers?

Specify the result, required sections, length, and rules for missing information. Meta recommends clearer instructions over lowering temperature and says Muse Spark performs best at temperature 1.0.

Get started

Start using Muse Spark 1.3 Contributor in opencode

One Spiral account for every tool your agent needs. No subscription; you pay per run.

Paste this into opencode:

Set up opencode

set up https://spiral.ai/SKILL.md
Are you an AI agent? See setup options