How to Use Muse Spark 1.2 Contributor in Codex
Muse Spark 1.2 Contributor suits complex debugging, codebase analysis, and multi-step agents. Unlike Muse Spark 1.2 in Standard mode, its prompts and responses may be used to train future Meta models.
Prompts to try with Muse Spark 1.2 Contributor in Codex
Copy an example into Codex, or ask in your own words.
Use Muse Spark 1.2 Contributor to investigate this project's failing tests. Trace the failure across related modules, make the smallest justified fix, and rerun the relevant checks.
Use Muse Spark 1.2 Contributor to map this repository's authentication flow. Identify where credentials are checked, where sessions are created, and which tests cover those paths.
Use Muse Spark 1.2 Contributor to refactor duplicated validation logic in this project. First identify the shared behavior, then update the callers and check that their existing behavior is preserved.
Use Muse Spark 1.2 Contributor to implement the interface shown in the reference image using this project's existing components. Check the rendered layout and test each interaction you add.
Use Muse Spark 1.2 Contributor to turn this project's specification into a working prototype. Plan the work, implement the main user flow, and verify it with the project's available checks.
How to set up Muse Spark 1.2 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 1.2 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-1.2-contributor", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Codex finds Muse Spark 1.2 Contributor on Spiral, shows the price and runs it.
Muse Spark 1.2 Contributor providers and prices
Spiral runs Muse Spark 1.2 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, or xhigh | medium | How much the model reasons. |
| Repetition penalty | 0 to 2 |
Every API field of Meta: Muse Spark 1.2 Contributor is on its tool page: open its card above.
What can you do with Muse Spark 1.2 Contributor in Codex?
Turn repository context into debugging work, coordinated refactors, or a working prototype with Muse Spark 1.2 Contributor. Give the agent a concrete behavior to achieve and checks it can run to assess the result.
Debug a problem across a repository
Trace an error through related modules, propose a fix, and check the behavior that originally failed.
Plan and carry out a refactor
Map the affected code, sequence changes across modules, and verify that the intended behavior survives.
Build a working prototype
Turn a detailed specification into a repository with application code and checks for its main behaviors.
Turn a visual reference into interface code
Use an image or demonstration video to guide layout, hierarchy, and interaction code.
Explain a chart
Extract visible values and units, then write a comparison grounded in the chart.
Summarize a demonstration video
Describe the sequence of actions and answer specific questions about what happens in the footage.
Extract structured records
Turn unstructured reports into JSON records with a defined set of fields.
Categorize incoming requests
Assign requests to predefined categories and return consistent structured labels.
More on Muse Spark 1.2 Contributor and Codex
Overview
Muse Spark 1.2 Contributor in other agents
Questions about Muse Spark 1.2 Contributor in Codex
Can Codex use Muse Spark 1.2 Contributor?
Yes. Add Spiral to Codex as an MCP server, and Codex can find and run Muse Spark 1.2 Contributor like any built-in tool.
How much does Muse Spark 1.2 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 1.2 Contributor in Codex?
No. Spiral runs Muse Spark 1.2 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 1.2 Contributor in Codex?
About two minutes: add the hosted server, then sign in.
Does Codex wait while Muse Spark 1.2 Contributor runs?
Muse Spark 1.2 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 1.2 Contributor best suited for?
Start with complex debugging, understanding a large codebase, and coding tasks that require several rounds of work. Muse Spark 1.2 was also trained on generating complete repositories and larger projects.
How much context can Muse Spark 1.2 Contributor handle?
Its context window is 1,048,576 tokens. That gives you room to provide substantial code or reference material for analysis.
Does Muse Spark 1.2 Contributor generate images or videos?
It returns text. It can analyze images and videos or write code based on a visual reference, but it does not return generated image or video media.
What does Contributor mean?
Content sent in Contributor mode may be used to train future Meta models. Meta says content sent in Standard mode is not used for that training.
Can Muse Spark 1.2 Contributor read charts?
Yes. Ask it to extract the relevant values, identify the units, and explain the comparison you care about.
Start using Muse Spark 1.2 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


