Amicore

Claude Cowork Cheat Sheet

Every feature, setting, and limitation — a bookmark-worthy reference for legal professionals

Last updated: April 24, 2026 Reference

Claude Cowork is Anthropic's agentic desktop product — Claude running inside an isolated Linux virtual machine on your Mac or Windows computer, able to execute multi-step tasks against files and applications you explicitly grant it access to. Over the last year it has grown from a single research preview into a composable stack: an instruction layer (Global Instructions, Folder Instructions, CLAUDE.md), an execution layer (Dispatch, Recurring Tasks, Sub-Agents), and a composition layer (Projects, Skills, Plugins). This cheat sheet is built to bookmark — each concept gets a crisp definition, a practical 'Use it when' line, and a link back to the canonical Anthropic documentation [1].

What Cowork Is (and Isn't)

  • +What it is: A desktop agent that runs multi-step tasks on your behalf using your local files, your installed applications, and connected tools. Think of it as Claude with a workstation of its own, sitting next to yours.
  • +Where it runs: Inside an isolated Linux virtual machine on your computer. Code and shell commands never touch your host operating system.
  • +What you grant: Folder-by-folder access. Claude can read and write only within directories you explicitly mount.
  • +What it isn't: A cloud service you share with a team. Cowork is tied to one desktop machine, one user, one active Claude Desktop app.

How Cowork Works Under the Hood

Cowork boots a lightweight, custom Linux virtual machine each time it runs. On macOS, it uses Apple's Virtualization Framework (the same technology powering tools like UTM and Tart) — a full VM with its own kernel, not a Docker-style container. The agent lives inside Ubuntu 22.04 with a disposable 10 GB root filesystem. Anything Claude does — browsing, writing code, running shell commands, calling APIs — happens inside that VM, not on your actual operating system [10].

Hardware-level isolation: The VM has its own filesystem. Even a catastrophic command inside the agent (a rogue script, an 'rm -rf /') cannot reach your host OS. When the session ends, the VM's state is discarded.
Folder mounting is explicit: Before Cowork can read a directory, you select it in the folder picker and grant permission. Claude sees only what you mount. Currently, the picker restricts mounts to your home directory — a known limitation for users with work drives outside %USERPROFILE% or ~/.
Network traffic is mediated: The VM does not freely access the open internet. Outbound requests are routed through host-side forwarding for policy enforcement and auditability, which matters for firms running DLP or egress controls.
Legal-audit angle: For firms worried about 'the AI has the run of my computer' — it does not. The trust boundary is the VM. Files leave your machine only if a mounted folder points to a synced cloud drive or a connector pushes them, both of which you authorize.

The Instruction Layer

Global Instructions, Folder Instructions, and CLAUDE.md

Three places you can write persistent guidance that Claude will read before every task. They compose — each layer adds to the ones above it.

Global Instructions: Persistent rules applied to every Cowork session, regardless of folder or project. Set in Settings > Cowork > Global Instructions. Anthropic suggests keeping them under ~500 words. Use them for who you are, how you want Claude to write, and any firm-wide non-negotiables (e.g., 'Never include client names in filenames'). Use it when: the rule should apply to every task on this machine.
Folder Instructions: Project-scoped rules that activate when Cowork is pointed at a specific local folder. Layered on top of Global Instructions. Perfect for client-matter conventions, naming rules, or practice-area-specific guidance. Use it when: the rule only applies inside one matter, one client, or one type of work.
CLAUDE.md files: Plain markdown files read automatically when Cowork enters a folder that contains one. Each folder in your working tree can have its own. Store reference material, style guides, or domain context alongside the work it governs. Use it when: the context belongs with the files — not in a global setting an admin has to maintain.

Global + Folder + CLAUDE.md — How They Layer

  • +Think of it as three nested envelopes:
  • +Global Instructions are defaults for every session. Your identity, tone preferences, and absolute rules belong here.
  • +Folder Instructions add project-specific context when you open a folder. They do not replace Global — they extend or override it for that directory.
  • +CLAUDE.md is file-level persistent context that travels with the folder itself. Even if you move the folder, share it via Dropbox, or re-open it months later, the context comes back because it lives in the directory.
  • +A practical pattern: Put your firm-wide style guide in Global, put per-client rules in Folder Instructions, and drop a CLAUDE.md inside each matter folder with matter-specific facts (parties, jurisdictions, key dates). Claude reads all three before starting work.

Deep Dive Coming: CLAUDE.md Files

  • +CLAUDE.md deserves its own article — where to put them, how long they should be, whether to commit them to your DMS, and how they interact with project memory.
  • +Read the dedicated guide: /research/claude-md-files-guide

The Execution Layer

Dispatch, Recurring Tasks, and Sub-Agents

How Cowork actually runs work. These features govern when tasks start, how often they repeat, and how many agents work in parallel.

Dispatch: Assign tasks to your desktop Claude from your phone. Launched March 17, 2026 as a research preview; now available in beta for both Pro and Max subscribers. You describe the task in the mobile app; Cowork executes it on your desktop while you are away from your desk. Use it when: you think of a task during a walk, a deposition break, or a commute, and want it done by the time you are back. Your desktop must stay open and awake [4].
Recurring Tasks (Scheduled Tasks): Automate Cowork tasks on a schedule or on demand. Common patterns: daily briefings from email and calendar, weekly matter status summaries, recurring competitive intelligence pulls, monthly billing prep. You describe the task once; Cowork runs it on cadence and delivers the finished output. Use it when: you find yourself doing the same pull or summary more than twice a month [3].
Sub-Agents: Specialized agents that handle a specific type of task end-to-end. Cowork can spawn sub-agents to work in parallel — a research sub-agent pulls sources while a drafting sub-agent builds the outline. Often bundled inside Plugins (where they are pre-configured), but power users can define their own. Use it when: a task has clearly parallel workstreams (research + drafting, data + visualization) that benefit from running simultaneously.

The Composition Layer

Projects, Skills, and Plugins

How you package and reuse work. The composition layer is where one-off tasks turn into repeatable systems.

Projects: Dedicated workspaces inside Claude Desktop where context, instructions, files, memory, and scheduled tasks live together. Unlike a standalone Cowork session — which forgets what happened when it closes — a Project remembers. Memory is scoped per Project, so what Claude learns while working on one matter does not leak to another. Use it when: the work will span more than a single session, or you want Claude to accumulate context over time [2].
Skills: Folders of instructions, scripts, and resources that teach Claude how to do a specific, repeatable task — a skill for drafting a deposition summary, a skill for generating a privilege log, a skill for producing a closing binder index. Skills work across chat, Cowork, and Claude Code. Use it when: you have a repeatable process you perform the same way every time and want to codify it [6].
Plugins: Installable bundles that combine Skills, Connectors, and Sub-Agents into a single package — like installing an app for a specific job function. Cowork ships with plugin libraries for functions including sales, finance, legal, marketing, HR, and operations. Use it when: you want a pre-configured setup for a domain rather than wiring up each skill, connector, and sub-agent yourself [5].

Critical Distinction: Project vs. Standalone Session

  • +This trips up almost every new Cowork user. The behavior is very different:
  • +Standalone Cowork session: Pick a folder, start work. No memory, no custom instructions beyond Global, no scheduled tasks. Fresh slate every time.
  • +Cowork Project: Dedicated workspace with persistent memory, project-specific instructions, attached folders, and scheduled tasks. Claude accumulates context across sessions.
  • +Practical rule: If this is one-shot work, a standalone session is fine. If you will touch the same matter again next week — or want scheduled tasks tied to it — create a Project.

The Folder Selector at the Bottom

The folder picker at the bottom of a Cowork session controls what the VM can see. When you click it and choose a folder, Cowork mounts that directory into the virtual machine's filesystem. From that moment on, Claude can read, write, create, and delete files within that folder — but only within that folder. Files outside are invisible. If Claude needs to reach into a sibling directory, you either mount it too or move the relevant files into the current mount. Currently, the picker restricts selections to your home directory, which can be awkward for attorneys who keep client files on mapped drives or secondary volumes (this is a tracked limitation, not intentional).

Access is a grant, not a default: Cowork has zero filesystem access at the start of every session. Mounting a folder is the explicit act that gives it any at all.
One folder, one session — historically: For most of 2025 and early 2026, mid-session folder additions required restarting. Anthropic has been shipping mid-session mounting improvements — check release notes if this matters for your workflow.
Symlinks and junctions can be rejected: The picker enforces the home-directory rule even against symlinked paths. Firms storing matter files on network shares cannot simply symlink them into home.

Deep Dive Coming: Folder Best Practices

  • +How you structure the folders you mount — one big bucket vs. per-matter directories, where to put CLAUDE.md files, what to exclude — has a large effect on Cowork's performance.
  • +Read the dedicated guide: /research/claude-cowork-folder-best-practices

MCP: The Plumbing Layer

The Model Context Protocol (MCP) is Anthropic's open standard for connecting Claude to external tools and data sources. It is the plumbing beneath Plugins and Connectors — the protocol that lets Claude talk to iManage, Salesforce, a document database, or a custom internal system. If Skills are the instructions and Plugins are the apps, MCP is the wiring. You will interact with MCP most often when installing a connector (a remote MCP server) or when your firm's IT team stands up a local MCP server to expose an internal tool to Claude [7][8][11].

Local MCP: Runs on your desktop. Useful for exposing local applications (your DMS client, a Python script) to Claude in Cowork.
Remote MCP (Custom Connectors): Runs on a server reachable over the internet. On Team and Enterprise, an owner authorizes it at the organization level. Note: remote MCP traffic flows from Anthropic's cloud to your MCP server, not from your desktop — relevant for data-egress policies.
Tool surface: An MCP server defines 'tools' (read data, create a record, send a message). Claude decides which tools to invoke while working on a task. You see the tool calls in the session log.

Deep Dive Coming: MCP Explained

  • +MCP deserves its own walk-through — how to evaluate a connector, how to stand one up safely for a firm, and what the data-flow implications are for privileged matters.
  • +Read the dedicated guide: /research/claude-mcp-explained

Cowork Is a One-Machine Tool

  • +Cowork is designed for a single desktop — not a multi-device workflow. This shapes everything about how you plan to use it.
  • +Memory lives on the machine: Project memory and scheduled tasks are stored on the specific computer running Cowork. Switching to your laptop means starting over there.
  • +No hand-off: You cannot start a session on your desktop, pause, and pick it up on another machine. There is no shared state.
  • +Mobile Dispatch is a partial exception: Pro and Max users can send new tasks from their phone to the desktop, but the desktop is still the one doing the work — it must stay open and awake.
  • +Practical implication for firms: If attorneys switch between office and home computers, each needs its own Cowork setup. Plan for duplicated Global Instructions and separate Projects per machine, or standardize on one primary workstation.

Usage Limits

Cowork uses the same usage pool as Claude chat and Claude Code on your plan. Hitting the limit on one affects the others. The resets differ by tier: Free and Pro reset every 5–8 hours on a rolling basis; Max plans reset weekly. There is no unlimited tier — Max 20× raises the ceiling substantially but does not remove it.

Shared pool: Claude.ai chat, Claude Code, and Cowork all draw from the same account-level budget. Heavy coding sessions reduce the budget available for Cowork tasks the same day.
Reset cadence: Free and Pro: rolling 5–8 hour windows. Max 5× and Max 20×: weekly resets. Plan long projects around the Max weekly window if you are on that tier.
Canonical reference: Anthropic maintains the authoritative plans and limits table at claude.com/pricing. Check it before sizing up — limits change as Anthropic tunes capacity [9].

Plan Tiers and Cowork Access

A snapshot of how Cowork availability maps to Claude plans as of April 2026. Prices are monthly. Verify at claude.com/pricing before purchasing.

Free

$0
  • +No Cowork access
  • +Web and mobile Claude chat only
  • +Useful for evaluation, not for Cowork workflows

Best for: Trial users deciding whether to subscribe

Pro

$20/month
  • +Cowork included
  • +Dispatch access (available in beta)
  • +Rolling 5–8 hour usage resets
  • +Projects, Skills, Plugins, MCP

Best for: Solo practitioners and small-firm attorneys doing individual Cowork work

Max 5×

$100/month
  • +Cowork + Dispatch (Max was first to receive Dispatch at launch)
  • +5× Pro usage allowance
  • +Weekly resets
  • +Extended Thinking

Best for: Attorneys and paralegals running Cowork for hours a day — document review, research, drafting

Max 20×

$200/month
  • +All Max 5× features
  • +20× Pro usage allowance
  • +Effectively all-day Cowork without hitting ceilings for most workflows

Best for: Power users treating Cowork as a continuous partner — litigation review, M&A diligence, multi-matter practices

Team

$25–$125/seat/month
  • +Cowork per seat (each user on their own desktop)
  • +Premium seat unlocks Claude Code
  • +Central billing and admin
  • +No model training on firm data by default

Best for: Firms with 5+ attorneys standardizing on Claude for knowledge work

Enterprise

Custom
  • +All Team features
  • +SSO, SCIM, audit logs, IP allowlisting
  • +Custom data retention
  • +HIPAA-ready offering available via BAA (BAA does not cover Cowork or Claude for Office — keep PHI workflows off those tools)

Best for: Firms with 50+ users needing compliance controls and custom terms

Current Limitations (from Anthropic's Help Center)

  • +Some Cowork capabilities are not yet available:
  • +Memory in projects only: Memory is supported within projects but is not retained across standalone Cowork sessions.
  • +No chat or artifact sharing: Sessions cannot be shared with others.
  • +Desktop app required: Cowork runs on your desktop computer via the Claude Desktop app. Pro and Max users can also message Claude from the mobile app while your desktop stays active. See Assign tasks to Claude from anywhere in Cowork for details.
  • +Session persistence: The Claude Desktop app must remain open and your computer must be awake for Claude to work on tasks. If you close the app or your computer goes to sleep, active tasks will stop.
  • +Source: Anthropic, 'Get started with Claude Cowork,' Claude Help Center.

Quick-Reference: Which Feature Do I Want?

A cheat-sheet within the cheat sheet. Match the problem to the tool.

I want Claude to behave a certain way in every session.

Global Instructions. Keep them under ~500 words.

I want rules that apply only to this client's folder.

Folder Instructions, or a CLAUDE.md file in that folder.

I want Claude to remember what we did last week.

Create a Project. Standalone sessions do not retain memory.

I want to send Claude a task from my phone.

Dispatch (Pro/Max). Desktop must stay open and awake.

I want a report every Monday morning.

Recurring Tasks (Scheduled Tasks) inside a Project.

I have a repeatable process I do identically each time.

Build a Skill. Works in chat, Cowork, and Claude Code.

I want a pre-built bundle for a practice area.

Install a Plugin — it wraps Skills, Connectors, and Sub-Agents.

I want Claude to read from my DMS or a firm system.

An MCP connector. Local for desktop-only tools, remote for internet-reachable systems (Team/Enterprise).

I want two parts of a task to run in parallel.

Sub-Agents — often set up for you inside a Plugin.

Getting Started Sensibly

A pragmatic sequence for a firm evaluating Cowork, minus the evangelism.

1

Install Claude Desktop and confirm your plan covers Cowork

Pro or above. Free does not include Cowork.

2

Write a minimal Global Instructions block

Your role, how you write, any absolute rules. Under 500 words. Resist the urge to list every preference — dilution is real.

3

Run your first standalone session against a low-stakes folder

Pick a non-privileged folder — a CLE outline, an internal memo, a research notes directory — and test a real task end to end.

4

Create your first Project when you hit the 'I wish it remembered' moment

Standalone sessions forget. The moment you notice yourself re-explaining context, promote that workstream to a Project.

5

Add a scheduled task only after the Project is stable

Recurring Tasks are high-leverage but only if the underlying task is reliable. Prove it manually first, then schedule.

6

Evaluate a Plugin before building Skills from scratch

Anthropic's plugin library covers common knowledge-work domains. Install before you author — the pre-wired Skills + Connectors will save hours.

Key Takeaways

  • 1.Cowork runs inside an isolated Linux VM on your desktop — code never touches your host OS, and Claude can read/write only in folders you explicitly mount.
  • 2.Three instruction layers stack: Global Instructions (every session) → Folder Instructions (per directory) → CLAUDE.md files (travel with the folder).
  • 3.Three execution features govern how work runs: Dispatch (from phone), Recurring Tasks (on schedule), Sub-Agents (in parallel).
  • 4.Three composition primitives turn ad-hoc work into systems: Projects (persistent memory), Skills (repeatable processes), Plugins (installable bundles).
  • 5.Standalone sessions have no memory. If you want Claude to remember across conversations, you need a Project.
  • 6.Cowork is single-machine. Memory and scheduled tasks live on the specific computer running the Claude Desktop app — no hand-off to another device.
  • 7.The desktop app must stay open and the computer must remain awake for tasks to run. Sleep = stopped tasks.
  • 8.Usage is shared across Claude chat, Claude Code, and Cowork on your plan. Free/Pro reset every 5–8 hours; Max resets weekly. See claude.com/pricing for authoritative limits.
  • 9.HIPAA-ready Enterprise BAAs do not cover Cowork today. Firms processing PHI should keep that workflow outside of Cowork.
  • 10.MCP is the plumbing beneath Plugins and Connectors — worth understanding before building firm-wide integrations.

References

  1. [1]Anthropic, "Get started with Claude Cowork," Claude Help Center.Link
  2. [2]Anthropic, "Organize your tasks with projects in Claude Cowork," Claude Help Center.Link
  3. [3]Anthropic, "Schedule recurring tasks in Claude Cowork," Claude Help Center.Link
  4. [4]Anthropic, "Assign tasks to Claude from anywhere in Cowork," Claude Help Center.Link
  5. [5]Anthropic, "Use plugins in Claude Cowork," Claude Help Center.Link
  6. [6]Anthropic, "What are Skills?" Claude Help Center.Link
  7. [7]Anthropic, "Getting Started with Local MCP Servers on Claude Desktop," Claude Help Center.Link
  8. [8]Anthropic, "Get started with custom connectors using remote MCP," Claude Help Center.Link
  9. [9]Anthropic, "Plans & Pricing — Claude by Anthropic."Link
  10. [10]Pvieito, "Inside Claude Cowork: How Anthropic Runs Claude Code in a Local VM on Your Mac," Jan. 2026.Link
  11. [11]Anthropic, "Introducing the Model Context Protocol."Link
Back to Research