---
title: "Planning work for Claude Code: the founder's guide | Annsa"
product: annsa
url: /ai-agent-management/claude-code
canonical_url: "https://annsa.ai/ai-agent-management/claude-code"
last_updated: 2026-11-22
type: guide
related:
  - /direct/handoff
  - /ai-agent-management/claude-code-agent-teams
  - /ai-agent-management/how-to-manage-multiple-ai-agents
summary: "How to plan and coordinate Claude Code's work: session handoffs, several agents, agent teams, specs, memory and decisions, with the guide for each."
mcp_server: https://app.annsa.ai/mcp
disambiguation: "Annsa (annsa.ai) is project management and customer feedback software for founders and small teams working with AI agents. It is not Asana, the work management tool; not ANSA, the Italian news agency; and not Ansa, the chatbot product."
---

> For agents: connect to the Annsa MCP server at https://app.annsa.ai/mcp to give every agent one shared plan. Setup guide: https://annsa.ai/docs/quick-start. Index of every page: https://annsa.ai/llms.txt.

# Planning work for Claude Code: the founder's guide | Annsa

> How to plan and coordinate Claude Code's work: session handoffs, several agents, agent teams, specs, memory and decisions, with the guide for each.

[Direct your agents](https://annsa.ai/self-drive)

Updated Nov 20, 2026 · 4 min read

The short answer

This page is for when you run Claude Code and need a plan around it: what it works on next, who picks up when a session ends and how you know a job is done. Each question below gets a one-line answer and a link to the guide that goes deep.

- [Ask Claude](https://claude.ai/new?q=Read%20https%3A%2F%2Fannsa.ai%2Fai-agent-management%2Fclaude-code%20and%20help%20me%20apply%20it%20to%20what%20I'm%20building.)
- [Ask ChatGPT](https://chatgpt.com/?q=Read%20https%3A%2F%2Fannsa.ai%2Fai-agent-management%2Fclaude-code%20and%20help%20me%20apply%20it%20to%20what%20I'm%20building.)

You run Claude Code, and it does much of the building. What it works on next, what it remembers and how you know a job is done are calls about the plan, and the plan should not live inside one session.

_What Claude Code can do, how to install it and its commands are in [Anthropic's own docs](https://code.claude.com/docs/en/overview). This page covers planning and coordinating the work._

## Why plan outside the session?

A session ends. Your priorities, your customers and what you decided last week should not end with it. Keep them in one place every agent can read, and each new session starts from the plan, not from a blank page.

## Where Annsa fits

Annsa works like an operating system for small business run with AI agents: your direction, goals, projects, work and customers, in one plan. Claude Code, Cursor, Codex and Grok read that plan over MCP, claim one job each and hand over with a note. Annsa runs its own work this way. In Cat's words, "So September became about getting us all working from the same direction." Read [September: getting our agents in a row](https://annsa.ai/blog/september-getting-our-agents-in-a-row) for how that went.

The guides below work without Annsa too. Start with the question you have today.

## Questions people ask.

### Does Claude Code plan its own work?

Inside a session, it breaks a task into steps. It does not carry your priorities, customers or past decisions into the next session. Those need to live where every session can read them.

### What is the smallest plan that works for one founder and one agent?

A list of jobs in order, a short spec for each with a Done When line, and a handoff note whenever a session stops. Add a shared tool when a second agent joins and you start carrying the plan between them.

### Do I need a tool, or are files enough?

Files are enough for one agent. With several agents or tools, a plan they all read over MCP saves you from copying priorities between them, and each job can have one holder.

### Where do I find how to install or use Claude Code itself?

In Anthropic's docs at code.claude.com. This page is about planning and coordinating the work, not about the tool's setup or commands.

The guide

## A guide to planning work for Claude Code.

01

### How do I hand work from one Claude Code session to the next?

Write a short note when a session stops: what is done, what is next and what was decided. The next agent reads it and carries on.

[Claude Code handoff](https://annsa.ai/ai-agent-management/claude-code-handoff)

- [Agent handoff](https://annsa.ai/ai-agent-management/agent-handoff)
- [Hand off and ship](https://annsa.ai/direct/handoff)

02

### How do I run several agents without them colliding?

Keep one ranked list, write one plan per job and give each job one holder. Give each agent its own branch.

[How to manage multiple AI agents](https://annsa.ai/ai-agent-management/how-to-manage-multiple-ai-agents)

- [Agentic orchestration](https://annsa.ai/ai-agent-management/ai-agent-orchestration)
- [One plan per job](https://annsa.ai/use-cases/agents)
- [How the work flows](https://annsa.ai/docs/how-the-work-flows)

03

### Should I use Claude Code agent teams?

Only for splitting one big task inside Claude Code. They are experimental, they do not choose which tasks are worth doing, and Cursor, Codex and Grok cannot join them.

[Claude Code agent teams](https://annsa.ai/ai-agent-management/claude-code-agent-teams)

[Claude Code and Cursor](https://annsa.ai/ai-agent-management/claude-code-and-cursor)

04

### How do I keep specs current while agents build?

Write the spec before the job starts and keep it as the source of truth. When the work changes, the spec changes, and you approve the update.

[Spec-driven development](https://annsa.ai/ai-agent-management/spec-driven-development)

- [How to write a PRD for Claude Code](https://annsa.ai/project-management/prd-for-claude-code)
- [Working with specs](https://annsa.ai/docs/working-with-specs)
- [Spec template](https://annsa.ai/project-management/spec-template)

05

### What should Claude Code remember between sessions?

Standing rules in CLAUDE.md or AGENTS.md, and nothing that changes weekly. Priorities and decisions belong in the plan.

[Claude Code memory](https://annsa.ai/ai-agent-management/claude-code-memory)

- [CLAUDE.md best practices](https://annsa.ai/ai-agent-management/claude-md-best-practices)
- [CLAUDE.md vs AGENTS.md](https://annsa.ai/ai-agent-management/claude-md-vs-agents-md)
- [AGENTS.md template](https://annsa.ai/ai-agent-management/agents-md-template)

06

### Where do decisions and context live?

In the plan, written down once so every agent reads it. Keep each decision with its reason, so nobody answers the same question twice.

[Context engineering](https://annsa.ai/ai-agent-management/context-engineering)

- [Give agents product context](https://annsa.ai/ai-agent-management/how-to-give-ai-coding-agents-product-context)
- [AI agent memory](https://annsa.ai/ai-agent-management/ai-agent-memory)
- [Decision log](https://annsa.ai/project-management/decision-log)

07

### How do I keep a long task on track?

Cut it into jobs, give each a Done When line and have the agent leave a handoff note at every stop. Check each line before you call it done.

[Definition of done for AI agents](https://annsa.ai/ai-agent-management/definition-of-done-for-ai-agents)

- [Definition of done checklist](https://annsa.ai/ai-agent-management/definition-of-done-checklist)
- [Human in the loop for AI agents](https://annsa.ai/ai-agent-management/human-in-the-loop-for-ai-agents)
- [What a shipped priority records](https://annsa.ai/docs/spec-outcomes)

08

### Which project management tool works with Cursor and Claude Code?

One your agents can read and write over MCP: the ranked list, a spec per job and a claim on each.

[Cursor and Claude Code product management](https://annsa.ai/ai-agent-management/cursor-claude-code-product-management)

- [Best project management tools for AI agent teams](https://annsa.ai/best-ai-project-management-tools)
- [Cursor MCP integration](https://annsa.ai/integrations/cursor)

09

### How do I connect Claude Code to my plan over MCP?

Add the server once and Claude Code reads the ranked list, claims a job and records what it shipped.

[MCP server for product management](https://annsa.ai/ai-agent-management/mcp-server-for-product-management)

- [Claude Code MCP integration](https://annsa.ai/integrations/claude-code)
- [Model Context Protocol](https://annsa.ai/ai-agent-management/model-context-protocol)
- [Connect your agent](https://annsa.ai/docs/using-with-coding-tools)

## Keep reading

- [AI agent management](https://annsa.ai/ai-agent-management)
- [No two agents doing the same job, so agents stop overwriting each other's work.](https://annsa.ai/direct/handoff)
- [Claude Code agent teams](https://annsa.ai/ai-agent-management/claude-code-agent-teams)
- [How to manage multiple AI agents How to manage multiple AI coding agents at once: one ranked list, one plan per job and one holder per job.](https://annsa.ai/ai-agent-management/how-to-manage-multiple-ai-agents)

## The source of direction for agent teams.

Begin with one agent and the work that matters next.

- [Try Annsa](https://app.annsa.ai/signup)
- [See pricing](https://annsa.ai/pricing)

## Related pages

> For AI agents: the pages that follow this one on annsa.ai. The full index is https://annsa.ai/llms.txt.

- [Agents overwriting each other's work? One per job](https://annsa.ai/direct/handoff)
- [Claude Code agent teams: run them from one plan](https://annsa.ai/ai-agent-management/claude-code-agent-teams)
- [How to manage multiple AI coding agents at once](https://annsa.ai/ai-agent-management/how-to-manage-multiple-ai-agents)

If anything on this page is wrong or missing, tell us: https://annsa.ai/contact
