Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By tmoody1973
Linear-driven build loop for Claude Code. A Linear issue is the spec (Intent / Acceptance / Verification); the skill builds to it, verifies against real data, and writes results back. A project = a milestone fanned into spec'd issues. Bundles the official Linear MCP server so install wires up both the workflow and the integration.
npx claudepluginhub tmoody1973/linear-build-plugin --plugin linear-buildA Claude Code plugin that turns Linear into your spec source for building software, and bundles the official Linear MCP server so installing it wires up both the workflow and the integration.
A Linear issue is the brief Claude reads before writing code — intent, acceptance criteria, and a verification checklist. Claude builds to it, proves it against real data, and writes the result back to the issue. A project = a milestone fanned into spec'd issues.
skills/linear-build/) — the workflow: build an issue, create an issue from intent, or kick off a whole project..mcp.json) — the official https://mcp.linear.app/mcp (Streamable HTTP, OAuth 2.1), registered as linear-server.docs/linear-with-claude-code.md) — the plain-English deep reference.| Trigger | What happens |
|---|---|
build RAD-42 / any TEAM-123 | Read the issue → align → build to its acceptance criteria → verification gate → close with evidence |
turn this into a Linear issue | Draft the Intent / Acceptance / Verification spec, confirm, create it |
create a Linear project for X | Create the project, fan it into spec'd issues, confirm the plan, then build the first |
This repo is a self-contained Claude Code plugin marketplace.
# 1. Add this repo as a marketplace (GitHub, or a local path)
/plugin marketplace add tmoody1973/linear-build-plugin
# or from a local clone:
# /plugin marketplace add ~/Documents/Projects/linear-build-plugin
# 2. Install the plugin
/plugin install linear-build@tarik-skills
# 3. Restart Claude Code so the skill + MCP server load
The Linear MCP uses OAuth. After install + restart, run:
/mcp
and complete the Linear sign-in for the linear-server connection. (Tools appear under the mcp__linear-server__* namespace.)
If you'd rather not use the plugin system:
# copy the skill
cp -r skills/linear-build ~/.claude/skills/
# add the MCP server (official setup command from Linear's docs)
claude mcp add --transport http linear-server https://mcp.linear.app/mcp
# then run /mcp in a session to authenticate
Every issue should carry these sections — that's what makes the workflow worth it:
## Intent
What you want and why. One or two plain sentences.
## Acceptance criteria
The finish line — checkable bullets.
- [ ] ...
## Verification checklist (prove it against reality)
How we'll prove each criterion with real data, not assertions.
- [ ] ...
## Out of scope
What this issue is NOT.
Specs that live in chat disappear, have no agreed finish line, and are ad hoc. A Linear issue fixes all three — and its verification checklist doubles as the proof gate before anything ships. See docs/linear-with-claude-code.md.
Official Linear MCP docs: https://linear.app/docs/mcp
External network access
Connects to servers outside your machine
Share bugs, ideas, or general feedback.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Harness-native ECC plugin for engineering teams - 63 agents, 251 skills, 79 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Memory compression system for Claude Code - persist context across sessions
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claim