How to Use Muse Spark 1.3 Contributor in Codex
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 Codex
Copy an example into Codex, 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.
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 Codex
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the hosted server
codex mcp add spiral --url https://api.spiral.ai/mcp
- Sign in
Codex opens the browser: sign in to Spiral and click Authorize. No API key. codex mcp list then shows Spiral.
codex mcp login spiral
Use the Spiral skill
- Send Codex 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 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: Codex 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.
Up to $0.00107 per run at the default inputs. $0.13 per 1M input tokens, $0.26 per 1M output tokens.
Settings you can ask for
Ask Codex for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Top k | a whole number from 0 | ||
| Top p | 0 to 1 | ||
| Max tokens | 1 to 943718 | The most output tokens to generate. | |
| Temperature | 0 to 2 | ||
| Reasoning effort | minimal, low, medium, high, xhigh, or max | medium | How much the model reasons. |
| Repetition penalty | 0 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 Codex?
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.
More on Muse Spark 1.3 Contributor and Codex
Overview
Muse Spark 1.3 Contributor in other agents
Questions about Muse Spark 1.3 Contributor in Codex
Can Codex use Muse Spark 1.3 Contributor?
Yes. Add Spiral to Codex as an MCP server, and Codex can find and run Muse Spark 1.3 Contributor like any built-in tool.
How much does Muse Spark 1.3 Contributor cost in Codex?
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 Codex plan is separate.
Do I need an OpenRouter account to use Muse Spark 1.3 Contributor in Codex?
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 Codex?
About two minutes: add the hosted server, then sign in.
Does Codex wait while Muse Spark 1.3 Contributor runs?
Muse Spark 1.3 Contributor runs in the background. Codex 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.
Start using Muse Spark 1.3 Contributor in Codex
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Codex:
set up https://spiral.ai/SKILL.md


