Shared Task List - Claude Code
Teammates claim and complete work independently from one list.
The shared task list is the coordination primitive for Agent Teams. Teammates claim tasks, do them, and mark them complete - no direct dispatching required.
What it does
The lead writes tasks to the shared list. Teammates watch the list, claim ones that match their skills, and post updates as they progress. Claims prevent double work. Statuses (pending, claimed, in-progress, completed, failed) make the team's state legible at a glance. It's the simplest coordination pattern that handles real parallelism.
When to use it
- Any Agent Team run - the shared list is always present.
- Patterns where any teammate can do any task (fungible workers).
- Visibility - a human can watch the list and understand progress.
- Recovery - if a teammate stalls, another can re-claim.
Gotchas
- Race conditions on claims are rare but possible. Watch for dual claims in logs.
- Tasks with unspoken dependencies cause deadlock. Use explicit task dependencies.
- Keep task descriptions actionable - vague tasks produce vague results.
Official docs: https://code.claude.com/docs/en/agent-teams.md#assign-and-claim-tasks
Technical content at the intersection of AI and development. Building with AI agents, Claude Code, and modern dev tools - then showing you exactly how it works.
Newsletter
Get the weekly deep dive
Tutorials on Claude Code, AI agents, and dev tools, delivered free every week.
Was this helpful?
Related Guides
Related Tools
Claude Code
Anthropic's agentic coding CLI. Runs in your terminal, edits files autonomously, spawns sub-agents, and maintains memory...
View Tool
Codeburn
Interactive TUI dashboard that shows exactly where your Claude Code and Cursor tokens are going, in real time.
View Tool
Claude Opus 4.7
Anthropic's flagship reasoning model. Best-in-class for coding, long-context analysis, and agentic workflows. 1M token c...
View Tool
Conductor
Mac app for running parallel Claude Code, Codex, and Cursor agents in isolated workspaces. Watch every agent work at onc...
View ToolRelated Videos
Open Design: Turn Websites into Design Assets for Cursor & Claude Code
Open Design: Open-Source n8n App That Turns Any Website into a Brand Kit, Design System, HTML + Images The video introduces Open Design, an MIT-licensed full-stack template that combines AI and n8n a...
Nimbalyst: The Open-Source Visual Workspace for Building with Codex and Claude Code
Nimbalyst Demo: A Visual Workspace for Codex + Claude Code with Kanban, Plans, and AI Commits Try it: https://nimbalyst.com/ Star Repo Here: https://github.com/Nimbalyst/nimbalyst This video demos N...
Composio: Connect OpenClaw & Claude Code to 1,000+ Apps via CLI
Composio: Connect AI Agents to 1,000+ Apps via CLI (Gmail, Google Docs/Sheets, Hacker News Workflows) Check out Composio here: http://dashboard.composio.dev/?utm_source=Youtube&utm_channel=0426&utm_
Related Posts
Claude Outages Are a Workflow Design Problem
Claude outages and 529 overloads expose whether your AI coding workflow has checkpoints, receipts, model-switch paths, a...
Claude Opus 4.8 Is an Agent Honesty Release
Claude Opus 4.8 looks like a benchmark bump, but the developer story is better honesty, dynamic workflows, and effort co...
Anthropic Sonnet 4.5 in Claude Code
Anthropic's Claude Sonnet 4.5 isn't just another model increment. The company claims they've observed it maintaining foc...
Terence Tao Digests the Jacobian Conjecture Counterexample: How Claude Fable 5 Broke an 87-Year-Old Math Problem
Terence Tao published a deep mathematical digestion of the Jacobian conjecture counterexample discovered by Claude Fable...
HalluSquatting Makes AI Coding Agents a Supply-Chain Problem
A July 2026 paper shows how hallucinated repository and skill names can become promptware delivery paths. The practical...
Securing AI Coding Agents: A Practical Threat Model for 2026
Prompt injection, sandbox escapes, and hallucinated dependencies are now documented, patched, CVE-numbered realities. He...
