# Which agent for which job

What each agent app is good at, organised by the job you need done. Every claim links to the vendor’s own documentation.

## Prickle doesn’t pick or run models.

You choose your agents and the apps they run in, on your own plans. Prickle routes work between people’s agents: it never calls a model and never asks for an AI login.

This is a guide to what each vendor documents, not a ranking. Models, plans and limits change every few weeks.

Checked against each vendor’s documentation on 17 October 2026.

## Start from the job.

Each job lists agents that fit and why. Often more than one fits: pick the one your team already has, with the right tools connected.

### A big refactor or a long task

It needs room to plan, split the work and keep going for a long time, then hand back a diff you can review.

- **Claude Code:** Subagents and background agents split the work, cloud sessions keep running when your computer is off, and current Claude models have a 1M-token context window by default. [1][2][3]
- **Codex:** Cloud tasks get their own workspace and keep working while your computer is asleep. Subagents start when you ask for them. [18][19]
- **Grok Build:** /goal stops only when reviewer subagents agree the work is done, and parallel subagents each work in their own worktree. [36][37]
- **Cursor:** Cloud agents run in isolated virtual machines, so your computer doesn’t need to stay online. [56]

### A quick fix

Small, close to the code and cheap. You want to see the change before it lands.

- **Cursor:** Its CLI has Agent, Plan and Ask modes, and it asks before using an MCP tool by default. [55][57]
- **Claude Code:** Plan mode blocks edits until you approve its plan. Fast mode makes Opus up to 2.5 times faster, at a higher price. [4][5]
- **Codex:** /model picks a lighter model and reasoning effort. On Plus, the efficient model allows many more messages per five hours. [16][22]
- **opencode:** Works with more than 75 providers and with local models, so a small job can run on a small model. [47]

### Design and assets

Images, video and checking a UI. Here the app matters more than the model: some make pictures and some can’t.

- **ChatGPT:** Generates images with gpt-image-2 in the desktop and web apps, and in Codex too. [28]
- **Grok:** The Grok app makes images and video with Imagine, with a watermark you can’t remove. Through xAI’s API, video clips run 1 to 15 seconds at up to 1080p. [43][45]
- **Claude:** Draws HTML or SVG diagrams and charts, but doesn’t generate photos or illustrations. [15]

### Research

Reading many sources and handing back something you can check.

- **ChatGPT:** Work mode takes multi-step research through to a document, spreadsheet or slides, in a managed cloud that keeps going after you close the app. [24][25]
- **Grok:** xAI’s X Search tool reads posts in real time, which suits questions about what people are saying right now. Through the API it’s billed per post read. [44]
- **Grok Build:** /deep-research runs a research task from the terminal. [37]
- **Claude:** Research can call your connectors’ tools, so it reads from the services you’ve connected. It does so without asking each time. [12]

### Reviewing a PR

A second look that can read everything and change nothing.

- **Codex:** /review checks uncommitted changes, a commit or a branch and reports findings without touching your working tree. codex exec runs read-only unless you allow edits. [16][17]
- **Grok Build:** Its read-only sandbox profile is meant for reviewing and auditing code. [40]
- **Claude Code:** Plan mode explores first and blocks edits until you approve a plan. Deny rules block in every mode. [5]
- **Cursor:** Ask mode is read-only: it explores the code without making changes. [55]

### Work that runs without you watching

Mentions only notify. Prickle’s runner is intended to wake an agent for an eligible task handoff; team staging currently stays in dry run until a launch profile is verified. Know what each client does when nobody is there to approve a step.

- **Claude Code:** claude -p prints text or JSON. A remote MCP server that needs an OAuth sign-in can’t complete it in a -p run, so sign in first. [7][8]
- **Codex:** codex exec is read-only by default and must run inside a git repository unless you tell it otherwise. [17]
- **Gemini CLI:** With trusted folders turned on, a run in a folder you haven’t trusted stops with an error. [33]
- **Grok Build:** Its sandbox is off by default. Choose a profile, such as workspace, before letting it run alone. [40]

## Each agent in short.

What each app is, what it does well, what to watch for, and whether it connects to Prickle today.

### Claude Code

Anthropic. In the terminal, VS Code, JetBrains, the desktop app and the web.

- **Good at:** Long coding work: subagents, background agents and cloud sessions that keep going when your computer is off. Current models have a 1M-token context window by default. [1][2][3]
- **Tools and permissions:** MCP over stdio and HTTP, with OAuth. Modes run from approving every step to auto, where a classifier reviews actions. Its sandbox covers shell commands only, and native Windows runs them unsandboxed. [5][6][7]
- **Cost:** A Pro, Max, Team or Enterprise plan, or API billing. Plan usage has a five-hour and a weekly window, shared with chat. [9][14]
- **Watch for:** Claude models only. Fast mode costs more and, on a plan, bills to usage credits. [3][4]

Prickle: Connects to a local Prickle server today. [Connect Claude Code to Prickle](https://app.useprickle.dev/docs/connect/claude-code)

### Claude desktop app

Anthropic. Chat, Cowork and Code tabs on macOS and Windows, with Linux in beta.

- **Good at:** Everyday work next to code. Cowork runs tasks on Anthropic’s servers while your computer sleeps; the Code tab runs Claude Code locally or in the cloud. [1][10][11]
- **Tools and permissions:** Custom connectors (remote MCP) connect from Anthropic’s cloud, so the server must be public. Local servers come as desktop extensions. The Free plan allows one custom connector. [12][13]
- **Cost:** The same plans and shared limits as Claude Code. The Code tab needs a paid plan. [1][14]
- **Watch for:** It can’t generate photos or illustrations. Cowork tasks that use local files or the browser need the app open. [11][15]

Prickle: Connects to a local Prickle server today. [Connect Claude Desktop to Prickle](https://app.useprickle.dev/docs/connect/claude-desktop)

### Codex

OpenAI. The Codex CLI, the IDE extension, the ChatGPT apps and Codex cloud.

- **Good at:** Cloud tasks that keep working while your computer is asleep, local code review, and subagents when you ask for them. [16][18][19]
- **Tools and permissions:** MCP over stdio and streamable HTTP, with a bearer token or OAuth. Read-only, workspace-write and full-access sandbox modes, enforced by the operating system. [20][21]
- **Cost:** A ChatGPT plan: Plus and above include the CLI, IDE and web. An API key covers the CLI and IDE but not cloud tasks. Limits vary by model. [22]
- **Watch for:** ChatGPT sign-in offers OpenAI models. The CLI also supports custom providers through a compatible Responses API endpoint. Cloud tasks and subagents use more of your allowance. On Linux, install bubblewrap for the sandbox. [18][21][22][23]

Prickle: Connects to a local Prickle server today. [Connect Codex to Prickle](https://app.useprickle.dev/docs/connect/codex)

### ChatGPT

OpenAI. Web, desktop and mobile apps.

- **Good at:** Work mode for multi-step tasks that end in a deliverable: research, documents, spreadsheets and slides. Image generation with gpt-image-2. [24][28]
- **Tools and permissions:** A custom MCP server needs a public HTTPS address or a Secure MCP Tunnel. In Business and Enterprise workspaces, publishing MCP apps is off until an admin allows it. [26][27]
- **Cost:** ChatGPT plans from Free and Go to Plus, Pro, Business and Enterprise. [22]
- **Watch for:** It connects from OpenAI’s cloud, so a Prickle server on your own computer needs a public address or a tunnel first. [26]

Prickle: Works on team staging over OAuth. Elsewhere it needs Prickle at a public address.

### Gemini CLI

Google. An open-source terminal agent.

- **Good at:** Open source and scriptable, with a sandbox you can turn on, backed by Seatbelt, Docker, Podman or gVisor. [29][32]
- **Tools and permissions:** MCP over stdio, SSE and HTTP, with OAuth. OAuth needs a browser on the same machine, so it fails over SSH. [31]
- **Cost:** Since 18 June 2026 it no longer serves Google AI Pro, Ultra or free personal use. It works with Code Assist Standard or Enterprise and paid Gemini API keys. [30]
- **Watch for:** Google points unpaid users to the Antigravity CLI and says Gemini CLI isn’t optimised for Gemini 4 Argon. Prickle doesn’t support the Antigravity CLI: Google’s terms for its consumer plans don’t allow another app to run it. [29][34]

Prickle: Connects to a local Prickle server today. [Connect Gemini CLI to Prickle](https://app.useprickle.dev/docs/connect/gemini-cli)

### Grok Build

xAI. A terminal agent, also headless and over ACP.

- **Good at:** Long tasks with /goal and reviewer subagents, /deep-research, and parallel subagents in their own worktrees. The grok-build-0.1 model has a 256,000-token context window. [36][37][41]
- **Tools and permissions:** MCP over stdio and HTTP, and it reads Claude Code and Cursor MCP configs too. It asks by default, and rm and git push always prompt. The sandbox is off by default. [38][39][40]
- **Cost:** The X Subscription (Free, Plus, Premium, Super, Ultra), with one usage pool shared across Grok and Cursor. An xAI API key also works. [35][42]
- **Watch for:** Blocking network access for child processes is enforced only on Linux. [40]

Prickle: Connects to a local Prickle server today. [Connect Grok Build to Prickle](https://app.useprickle.dev/docs/connect/grok-build)

### opencode

Anomaly (SST). An open-source terminal app, desktop app and IDE extension.

- **Good at:** Choice: more than 75 providers, local models, and sign-in with some subscriptions (ChatGPT Plus or Pro, GitHub Copilot, GitLab Duo, SuperGrok). Plan and Build modes keep looking separate from changing. [46][47]
- **Tools and permissions:** Local and remote MCP, with OAuth started for you. Allow, ask and deny rules, with most actions allowed by default. No sandbox is documented. [48][49]
- **Cost:** Your provider’s pricing, or opencode’s own pay-as-you-go Zen or Go subscription. [50][51]
- **Watch for:** MCP servers fill the context window. Its docs say Anthropic prohibits using Claude Pro or Max through opencode plugins. [47][48]

Prickle: Connects to a local Prickle server today. [Connect opencode to Prickle](https://app.useprickle.dev/docs/connect/opencode)

### Cursor

Anysphere. An editor, a CLI and cloud agents.

- **Good at:** Working in the editor with Agent, Plan and Ask modes, and cloud agents you can start from the web, Slack, GitHub or Linear. Models from many vendors plus its own. [54][55][56]
- **Tools and permissions:** MCP over stdio, SSE and HTTP, with OAuth, asking before each tool by default. Its own docs say auto-review is not a security boundary. [57][58]
- **Cost:** Part of The X Subscription, with a weekly pool shared with Grok. Plus has no third-party models; Premium and above pay API list price for them. [52][53]
- **Watch for:** Cloud agents need a paid plan and bill at API pricing. [56]

Prickle: Not verified with Prickle yet.

## Using this in Prickle.

What an agent can do depends as much on the tools its owner connected (a design tool, a payments account, an analytics board) as on its model. Two teammates on the same app can be good at very different jobs.

In a project room, hand the job to the teammate whose agent fits. Prickle carries the handoff through that owner’s permission rules and records it. The work runs in their app, on their plan.

When you want a second opinion, ask a teammate whose agent runs a different model from the one that did the work.

## Sources

Vendor documentation, each opened on 17 October 2026. Follow the link before relying on a plan, a limit or a model name.

1. [Claude Code overview](https://code.claude.com/docs/en/overview), Anthropic, checked 2026-10-17
2. [Claude Code on the web](https://code.claude.com/docs/en/claude-code-on-the-web), Anthropic, checked 2026-10-17
3. [Claude Code model configuration](https://code.claude.com/docs/en/model-config), Anthropic, checked 2026-10-17
4. [Claude Code fast mode](https://code.claude.com/docs/en/fast-mode), Anthropic, checked 2026-10-17
5. [Claude Code permission modes](https://code.claude.com/docs/en/permission-modes), Anthropic, checked 2026-10-17
6. [Claude Code sandboxing](https://code.claude.com/docs/en/sandboxing), Anthropic, checked 2026-10-17
7. [Connect Claude Code to tools via MCP](https://code.claude.com/docs/en/mcp), Anthropic, checked 2026-10-17
8. [Run Claude Code programmatically](https://code.claude.com/docs/en/headless), Anthropic, checked 2026-10-17
9. [Manage costs in Claude Code](https://code.claude.com/docs/en/costs), Anthropic, checked 2026-10-17
10. [Claude Code in the desktop app](https://code.claude.com/docs/en/desktop), Anthropic, checked 2026-10-17
11. [Get started with Cowork](https://support.claude.com/en/articles/13345190-get-started-with-cowork), Anthropic, checked 2026-10-17
12. [Custom connectors using remote MCP](https://support.claude.com/en/articles/11175166-get-started-with-custom-connectors-using-remote-mcp), Anthropic, checked 2026-10-17
13. [Local MCP servers on Claude Desktop](https://support.claude.com/en/articles/10949351-getting-started-with-local-mcp-servers-on-claude-desktop), Anthropic, checked 2026-10-17
14. [Understanding usage and length limits](https://support.claude.com/en/articles/11647753-understanding-usage-and-length-limits), Anthropic, checked 2026-10-17
15. [Can Claude generate images?](https://support.claude.com/en/articles/9002504-can-claude-generate-images), Anthropic, checked 2026-10-17
16. [Codex CLI](https://learn.chatgpt.com/docs/codex/cli), OpenAI, checked 2026-10-17
17. [Codex non-interactive mode](https://learn.chatgpt.com/docs/non-interactive-mode), OpenAI, checked 2026-10-17
18. [Codex subagents](https://learn.chatgpt.com/docs/agent-configuration/subagents), OpenAI, checked 2026-10-17
19. [Codex cloud](https://learn.chatgpt.com/docs/cloud), OpenAI, checked 2026-10-17
20. [Codex and MCP](https://learn.chatgpt.com/docs/extend/mcp?surface=cli), OpenAI, checked 2026-10-17
21. [Codex sandboxing](https://learn.chatgpt.com/docs/sandboxing), OpenAI, checked 2026-10-17
22. [Codex pricing and usage limits](https://learn.chatgpt.com/docs/pricing), OpenAI, checked 2026-10-17
23. [Codex models](https://learn.chatgpt.com/docs/models), OpenAI, checked 2026-10-17
24. [ChatGPT on the web](https://learn.chatgpt.com/docs/web), OpenAI, checked 2026-10-17
25. [Using ChatGPT](https://learn.chatgpt.com/docs/use-chatgpt), OpenAI, checked 2026-10-17
26. [Connect a plugin to ChatGPT](https://developers.openai.com/plugins/deploy/connect-chatgpt), OpenAI, checked 2026-10-17
27. [MCP in ChatGPT](https://learn.chatgpt.com/docs/extend/mcp?surface=chatgpt), OpenAI, checked 2026-10-17
28. [Image generation](https://learn.chatgpt.com/docs/image-generation), OpenAI, checked 2026-10-17
29. [Gemini CLI documentation](https://geminicli.com/docs), Google, checked 2026-10-17
30. [Transitioning Gemini CLI to Antigravity CLI](https://developers.googleblog.com/an-important-update-transitioning-gemini-cli-to-antigravity-cli/), Google, checked 2026-10-17
31. [Gemini CLI MCP servers](https://geminicli.com/docs/tools/mcp-server/), Google, checked 2026-10-17
32. [Gemini CLI sandboxing](https://geminicli.com/docs/cli/sandbox/), Google, checked 2026-10-17
33. [Gemini CLI trusted folders](https://geminicli.com/docs/cli/trusted-folders/), Google, checked 2026-10-17
34. [Antigravity FAQ](https://antigravity.google/docs/faq), Google, checked 2026-10-17
35. [Grok Build overview](https://docs.x.ai/build/overview), xAI, checked 2026-10-17
36. [Grok Build CLI announcement](https://x.ai/news/grok-build-cli), xAI, checked 2026-10-17
37. [Grok Build modes and commands](https://docs.x.ai/build/modes-and-commands), xAI, checked 2026-10-17
38. [Grok Build MCP servers](https://docs.x.ai/build/features/mcp-servers), xAI, checked 2026-10-17
39. [Grok Build permissions](https://docs.x.ai/build/features/permissions), xAI, checked 2026-10-17
40. [Grok Build sandbox](https://docs.x.ai/build/features/sandbox), xAI, checked 2026-10-17
41. [grok-build-0.1 model](https://docs.x.ai/developers/models/grok-build-0.1), xAI, checked 2026-10-17
42. [The X Subscription pricing](https://docs.x.ai/x-subscription/pricing), xAI, checked 2026-10-17
43. [Grok FAQ](https://docs.x.ai/grok/faq), xAI, checked 2026-10-17
44. [X Search tool](https://docs.x.ai/developers/tools/x-search), xAI, checked 2026-10-17
45. [Video generation](https://docs.x.ai/developers/model-capabilities/video/generation), xAI, checked 2026-10-17
46. [opencode documentation](https://opencode.ai/docs), opencode, checked 2026-10-17
47. [opencode providers](https://opencode.ai/docs/providers/), opencode, checked 2026-10-17
48. [opencode MCP servers](https://opencode.ai/docs/mcp-servers/), opencode, checked 2026-10-17
49. [opencode permissions](https://opencode.ai/docs/permissions/), opencode, checked 2026-10-17
50. [opencode Zen](https://opencode.ai/docs/zen/), opencode, checked 2026-10-17
51. [opencode Go](https://opencode.ai/docs/go/), opencode, checked 2026-10-17
52. [Cursor pricing](https://cursor.com/help/account-and-billing/pricing), Cursor, checked 2026-10-17
53. [Cursor usage limits](https://cursor.com/help/models-and-usage/usage-limits), Cursor, checked 2026-10-17
54. [Cursor models and pricing](https://cursor.com/docs/models-and-pricing), Cursor, checked 2026-10-17
55. [Cursor CLI overview](https://cursor.com/docs/cli/overview), Cursor, checked 2026-10-17
56. [Cursor cloud agents](https://cursor.com/docs/cloud-agent), Cursor, checked 2026-10-17
57. [Cursor MCP](https://cursor.com/docs/mcp), Cursor, checked 2026-10-17
58. [Cursor run modes](https://cursor.com/docs/agent/security/run-modes), Cursor, checked 2026-10-17

[Runner setup and launch limits](https://app.useprickle.dev/docs/runner)

[People & agents](https://app.useprickle.dev/docs/concepts/people-and-agents)

[Quickstart](https://app.useprickle.dev/docs/quickstart)

[Read online](https://app.useprickle.dev/docs/agents/choosing)