tunahanaliozturk/partner-center-mcp
MCP server Claude CodeCodexCursor +2
Unofficial Partner Center REST API knowledge & codegen assistant (scenarios, auth, errors). Runs locally from the partner-center-mcp npm package.
Plugin Claude Code
Atelier agent-orchestration plugin marketplace.
Plugin Claude Code
Agent-orchestration plugin: a lead reviews a plan, gates on user approval, and routes tasks to specialist agents by capability.
Agent
Implements and refactors server-side code — APIs, services, business logic — and writes its own tests. Pick for backend implementation work.
Agent
Reviews task output for correctness, clarity, and maintainability after it passes spec review.
Agent
Implements data work — schema, migrations, queries, pipelines — and models data structures. Pick for database and data-pipeline work.
Agent
Writes and updates documentation — README, API docs, guides. Pick for documentation tasks.
Agent
Implements and refactors UI code — components, styling, state — and writes its own tests. Pick for frontend implementation work.
Agent
Implements and configures infrastructure — CI/CD, containers, IaC, deployment — and automates operational tasks. Pick for infra work.
Agent
Reviews a draft plan, gates on user approval, decomposes it into a task graph, and routes each task to the best-matched specialist agent.
Agent
Builds and optimizes machine-learning components — data pipelines, training, evaluation, and inference integration.
Agent
Builds and refactors mobile apps (iOS, Android, React Native) — UI, navigation, platform integration, and release builds.
Agent
Drafts an implementation plan as ordered steps with explicit dependencies, ready for the lead to review.
Agent
Writes and automates tests — unit, integration, and end-to-end — and hardens suites for reliability and coverage.
Agent
Reviews changes for security issues — injection, authz, secrets, unsafe dependencies. Cross-cutting; the lead calls it by name.
Agent
Checks that a task output matches its assigned task and the approved plan, with nothing missing and nothing extra.
Command
Show the Atelier crew and its capability coverage — agents by layer, task kinds, and routing gaps.
Command
Show the tasks that can start now — pending tasks whose dependencies are all done.
Command
Plan a goal, review it as the lead, get user approval, then dispatch tasks to specialist agents by capability.
Command
Draft and lead-review a plan for a goal and present it for approval, without starting any work.
Command
Show per-mission telemetry — total tokens and duration, a per-agent breakdown, the costliest task, and any done tasks missing metrics.
Command
Continue the most recent Atelier mission from where it left off, without re-approving the plan.
Command
Retry a blocked task in the current Atelier mission, or all blocked tasks if no id is given.
Command
Show the current Atelier mission board — progress, grouped tasks, the ready set, and a dependency graph.