Codex + Linear
Codex runs the task; the Linear connector supplies only the operations and resources allowed by the account you authorize. The Composer selects Codex, asks for Linear access before sending, and keeps both choices in one task draft.
How the combination works
Codex plans and executes. Linear supplies authorized app access.
Codex owns the coding-agent loop: it explores the repository, changes files, runs commands, and returns evidence from the cloud workspace.
Linear helps streamline software projects, sprints, tasks, and bug tracking. It's built for high-performance teams.
Codex
Owns the task loop, model calls, cloud computer, tool choices, progress and final result.
Linear connector
Supplies the currently exposed operations for the authorized Linear account. It does not promise every feature in the Linear product.
Permission boundary
The connected identity, granted provider scopes, organization policy, resource sharing and the task's explicit instruction all constrain what Codex can do.
Setup and first task
Connect one Linear account and verify one known resource.
The Composer preselects Codex with GPT-5.6 Sol. Start read-only when possible, then expand to write operations only after the account and resource boundary are clear.
Open the Codex Composer
The Composer above carries Codex, GPT-5.6 Sol, and Linear. Add a precise target and expected result; the draft stays on this page during sign-in or connector authorization.
Authorize the intended Linear account
Review the Linear workspace, authorized identity and requested scopes. Distinguish read access from permission to create or modify issues.
Run and verify a bounded task
Ask the agent to inspect a specific issue and summarize its acceptance criteria and unresolved dependencies without changing its status. Compare the returned issue identifier, status and details with Linear. For an authorized update, inspect the actual issue after the operation.
Access, cost and limits
What to verify before scaling Codex + Linear
Software engineering tasks that benefit from Codex's repository navigation, command execution, and iterative implementation loop.
Establish with the first run
- Codex and GPT-5.6 Sol remain selected after sign-in.
- Linear shows the intended connected account before the task is sent.
- The returned data matches one known source resource, with write actions excluded until separately authorized.
Still depends on your setup
- A catalog listing does not guarantee every Linear website feature is available as an agent operation.
- OAuth scopes do not replace organization policy, resource sharing or a precise task instruction.
- Total task cost can include model tokens, active computer time, paid tools, connectors and the provider's own plan or quota.
Verification and recovery
Check Linear itself before trusting the result.
Compare the returned issue identifier, status and details with Linear. For an authorized update, inspect the actual issue after the operation.
Connection troubleshooting
Check the workspace and team access of the connected identity. Confirm the requested operation is exposed before assuming an OAuth connection allows it.
Writes need explicit scope
Name the target record and exact allowed change. A request to summarize, analyze or draft does not authorize sending, publishing or deleting.
Re-check current state
For decisions or follow-up writes, open the resource in Linear and check its current state. A successful earlier read may already be stale.
Common questions
Related resources