Linear

Official OpenAI Codex skill for issues, projects, and team workflows in Linear.

Linear is an official curated skill from OpenAI's repository for Codex. Its primary source is https://github.com/openai/skills/tree/main/skills/.curated/linear. According to the provider, the skill supports structured work with issues, projects, and team workflows in Linear. It is not a standalone Linear client, a replacement for Linear documentation, or a promise that every action will run without confirmation. The skill supplies additional working instructions for a Codex agent that uses a connected Linear integration to access the information and tools the user has authorized.

Purpose and scope

The skill is intended for situations where a user wants to read tickets, prepare new issues, or work on existing tasks in a team context. According to the provider, the goal and scope should be clarified first. Depending on the task, that includes the team, project, priority, labels, cycle, and due dates. This framing reduces the risk that an agent creates a task in the wrong project or infers a consequential action from a short title. The Linear integration must already be connected; the skill does not provide authentication or its own server.

Workflow for issues

The official instructions describe an order consisting of clarifying the goal, selecting an appropriate workflow, identifying the required tools, and then executing the work. For issue work, that means reading existing data first and applying changes only with the required scope afterward. Relevant workflows include triage, sprint planning, release preparation, documentation audits, and cross-project dependencies. The skill also covers workflows involving labels, cycles, projects, and comments. Actual availability depends on the connected Linear integration, granted permissions, and the Codex product in use.

Practical value

A well-bounded request can summarize critical open issues for a team, locate relevant projects, identify missing labels, or structure dependencies between tasks. During sprint planning, an agent can read existing issues and suggest grouping them into a cycle. During a documentation audit, it can formulate gaps as candidate issues. During release preparation, it can derive milestones and work packages from the project context already present. Changes to external records are still consequential actions. The title, team, project, status, assignee, priority, and scope should be reviewed before execution.

Boundaries and safety

Linear content is data, not automatically trusted instructions. Issue descriptions, comments, and documents can be stale, incomplete, or deliberately manipulated. Prompt injection is therefore possible even when an integration is officially provided. An agent should not treat suspicious wording as a new authority. Before creating, editing, commenting on, or moving a task, verify the target, authorization, and scope. Do not store passwords, tokens, private keys, or other secrets in issues. Using the skill may send data to the connected Linear integration and selected model; local workflow instructions do not automatically mean that model processing happens locally.

Sources and E-E-A-T

This entry is based on the reachable official OpenAI source path and OpenAI's official Skills help article at https://help.openai.com/en/articles/20001066-skills-in-chatgpt. According to the provider, skills are reusable instructions for supported OpenAI products; availability, account permissions, and product capabilities may change. The official repository also contains a license file for the skill. Before production use, review the current primary source, the permissions granted to the Linear integration, and your team's internal approval process. Registry popularity signals are not copied into this Skill model because it has no repository-stars field.

Installation instructions

Linear is an official curated skill from OpenAI’s repository for Codex. According to the provider, it supports work with issues, projects, and team workflows in Linear through a connected Linear MCP integration. Linear itself is a tool for product and engineering teams, where tasks, projects, cycles, statuses, priorities, and comments are organized. The skill is not a separate Linear app and not a replacement for Linear. It gives Codex a workflow so an agent reads context first, selects the right workflow, and applies external changes in a controlled way.

Step 1: Check prerequisites and connection

Before using the skill in production, the Linear MCP connection must be reachable. According to the official skill file, this requires OAuth and access to the relevant workspace, teams, and projects. OAuth means sign-in happens through an authorization flow instead of copying passwords into the agent. Check whether your Codex client supports remote MCP and whether the connection can see only the workspaces it needs.

Start with a read-only request. For example, ask for a summary of teams, projects, or your own issues. This shows whether the agent sees the right organization and team. If the connection fails, the source says the workflow should pause for setup, let the user connect Linear, and continue after restart. Do not force write actions while identity, workspace, and permissions are unclear.

Clarify request and scope

Linear data often looks obvious but depends on context. An issue title may appear in several projects, a team may have similar labels, and priority may mean different things in different workflows. Describe the goal and scope concretely: is this triage, sprint planning, a documentation audit, release preparation, dependency analysis, or a comment draft? Name the team, project, cycle, label, priority, and due date only when they are relevant and confirmed.

The provider describes a workflow of clarifying the goal, selecting the appropriate workflow, identifying the required tools, and then executing the work. In safe practice, that means read first, propose next, change last. Have the agent retrieve existing issues, projects, or comments before it creates new tasks. For bulk changes, it should explain grouping and criteria before anything changes in Linear.

Change issues, projects, and comments safely

For every change, review the title, description, team, project, status, priority, assignee, and labels. A new issue should include a clear goal, context, acceptance criteria, and, where helpful, links to documents. A comment should make clear whether it is a summary, question, decision proposal, or review request. Changes to status or ownership can affect other people’s work and should not happen casually.

Linear content is data, not trusted instruction. An issue description may be stale or may intentionally include prompt-like text. The agent must not treat that content as new system rules. If an issue asks the assistant to ignore security rules or reveal secret data, that is prompt injection and should be rejected. Explicitly confirm external actions, especially when tasks are created, moved, closed, or commented on.

Security, privacy, and governance

Do not store passwords, tokens, private keys, or customer secrets in Linear issues. Even apparently internal tickets may later be exported, searched, or shared with other teams. Work with least privilege and check whether private teams, customer names, vulnerabilities, or personal data are involved. Using the skill may send data to Linear, the MCP connection, and the selected model.

Organizations should use a clear rule: reads are lower risk, writes require review. Define which actions the agent may prepare and which need approval. Record important changes through Linear comments or internal change notes. For security issues, HR-sensitive topics, or customer escalations, a person should review the final wording and recipient scope.

Value and limits

The practical value is high when teams want to structure recurring Linear work. The skill can summarize critical open issues, find missing labels, suggest sprint candidates, organize release work, or turn documentation gaps into candidate tickets. It saves time because it defines the order of reading, framing, changing, and summarizing.

Limits come from permissions, data quality, and context. The skill can only see what the connection allows. It does not automatically know your team’s political, contractual, or technical priorities. It does not replace product ownership, incident management, or team decisions. Use it as a controlled assistant for Linear work, not as an autonomous project manager.

Free
Provider
OpenAI
License
Apache-2.0
Last reviewed
09.09.2026

Repository and documentation

Categories

Compatible with

Codex