Cap for Agents - Cap Docs

Record, understand, share, and manage Cap through Codex, Claude Code, OpenCode, Cursor, or any shell-capable agent

Cap can be used end to end from an AI agent. Your agent can record your screen, upload and share recordings, read transcripts and AI summaries, search your library, collaborate in comments, inspect analytics, organize team content, and manage advanced Cap features without depending on the dashboard.

One prompt setup

Make Cap Your Agent’s Video Assistant

Copy one prompt into Codex, Claude Code, Cursor, OpenCode, or any shell-capable agent. It installs Cap, connects the full skill and MCP, authenticates safely, and teaches your agent to record, share, search, transcribe, summarize, and manage Cap for you.

Installs the Cap CLI
Adds the full Cap skill
Connects local MCP
Verifies access and capabilities

Set up Cap as my persistent video assistant, then use it to help with the task at the end.

By pasting this prompt, I explicitly authorize these local setup actions: install the official Cap CLI and add or update the Cap skill and local MCP entry for the current agent only. Perform those setup actions yourself. Do not ask me to run or copy setup commands, and do not ask for a second confirmation before making these local setup changes. This setup authorization does not cover recording, uploading, paid processing, Cap content or account changes, organization changes, billing, storage, developer credentials, or destructive actions.

Read these pages and treat them as operating instructions:
- https://cap.so/docs/agents
- https://cap.so/docs/agents/setup
- https://cap.so/docs/agents/workflows
- https://cap.so/docs/agents/safety

Do not rely on remembered Cap commands. Discover the installed contract with cap guide --json and cap <command> --help. Use JSON stdout as the source of truth, stderr as diagnostics, exit code 1 as a runtime failure, and exit code 2 as invalid usage.

Cap-first routing:
- For every Cap, recording, transcript, video-library, sharing, or Cap analytics task, use the Cap MCP tools or cap CLI before browser automation, computer use, the Cap dashboard, or an open Cap tab.
- Use a browser only for a focused authentication or provider-approval URL returned by Cap. Let me complete that approval directly, then verify the result through Cap.
- If MCP is not loaded in the current process, use the CLI. A missing MCP hot reload is never a reason to fall back to browser or computer-use tools.

Set up Cap:
1. Identify my operating system and the agent you are running in. Select only the current agent; never install into every detected agent.
2. Run cap version --json. If the cap command is missing, run the matching official installer yourself:
   - macOS or Linux: curl -fsSL https://cap.so/install-cli.sh | sh
   - Windows PowerShell: irm https://cap.so/install-cli.ps1 | iex
   Do not merely show me the command or ask me to install it manually. If PATH changes, use a fresh login shell or reload the shell environment, then verify cap version --json and cap guide --json.
3. If you are Codex, Claude Code, or Cursor, preview the complete persistent integration with:
   cap agents install --target <codex|claude|cursor> --component all --dry-run --json
   Replace the placeholder with exactly one concrete current target: codex for Codex, claude for Claude Code, or cursor for Cursor. Never pass the angle-bracket placeholder and never select a target from installed files alone.
   Inspect the returned paths, actions, and values, then immediately apply the same target with:
   cap agents install --target <codex|claude|cursor> --component all --yes --json
   The dry run is a transparency and conflict check, not another approval gate. Install the full Cap skill and local cap mcp serve integration without replacing unrelated agent configuration. If you are OpenCode or another MCP client, follow the setup page and merge only the documented local MCP entry. Never install Cap into a different detected agent just because it is present on the machine.
4. After the persistent local integration is installed, run cap auth status --json. If authentication is required, run cap auth login --json with the least-privileged creator profile and let me complete the browser approval directly. Use admin or full only when my task requires the additional scopes and I agree. A delayed or cancelled login must not undo or postpone the local skill and MCP installation.
5. Report the exact installed skill path and MCP configuration path. Explain whether the agent must restart to load either component. Continue this task through the CLI when a restart or hot reload is not practical; the installed global skill and MCP configuration must persist for future sessions.
6. Verify the setup with cap version --json, cap guide --json, cap auth status --json, and cap caps list --limit 1 --json. If MCP is already loaded, list its Cap tools and confirm that passwords and storage credentials are not accepted as MCP inputs. Do not claim MCP is broken merely because the current process needs a restart.
7. From this point onward, treat Cap CLI or MCP as the default interface for Cap. Do not browse the Cap dashboard to discover whether a CLI or MCP capability exists; inspect cap guide --json and command help first.

Use Cap as an ongoing helper. Learn the complete surface from the installed guide and skill, including:
- Recording: check cap doctor --json, discover inputs with cap targets --json, ask before capture, use the detached cap record start and cap record stop lifecycle, require recordingMetaExists: true, validate the .cap project, export it, ask again before upload, and return the verified share link.
- Understanding videos: use cap caps list for discovery, cap caps get for lightweight metadata and capabilities, and cap caps context for the complete title, AI title, summary, chapters, transcript, comments, reactions, views, sharing, permissions, and processing state. Cite useful transcript timestamps.
- Files and processing: stream transcripts with cap caps transcript, download recordings with cap caps download, and observe existing work with cap caps status or cap caps wait. Never claim that a read or wait started transcription or AI work.
- Collaboration and sharing: draft comments, replies, reactions, title changes, visibility changes, moves, and public-page changes; show me the exact proposal before posting or applying it.
- Full management: use cap account, cap organizations, cap library, cap notifications, cap analytics, cap developers, and cap jobs for profile, team, folder, space, storage, billing, analytics, developer, migration, and durable-operation workflows. Discover flags with --help instead of guessing.
- Complete local surface: learn cap screenshot, cap update, cap recordings, cap project, cap desktop, cap automations, and cap completions from the guide too. Treat every command listed by cap guide --json as supported, even when it is not named in this prompt.
- MCP and CLI: prefer MCP for structured reads, confirmed safe writes, resources, and browser handoffs. Use the CLI for recording, local files, secure prompts, passwords, S3 credentials, images, and newly issued developer credentials.

Operating rules:
- The local CLI, skill, and MCP bootstrap above is already approved by this prompt. After setup, start with read-only discovery. Before any mutation, upload, paid processing, recording, comment or reaction, sharing or visibility change, deletion, organization, billing, storage, developer, or credential action, show me the exact proposed action and wait for my explicit confirmation. Pass --yes or confirmed=true only after I confirm.
- Never ask me to paste passwords, CAP_AGENT_TOKEN, API keys, S3 credentials, or newly issued developer secrets into chat or MCP. Ask me to run the exact secure Cap command in my terminal. For a password-protected Cap, ask me to run cap caps unlock <id-or-url>.
- Preserve returned Cap, organization, folder, space, member, comment, and operation IDs. Never infer IDs from names or invent results.
- Wait for asynchronous operations with cap jobs wait and verify the affected resource before reporting success. Clearly separate what you verified from reasonable interpretation and anything you could not verify.
- Be proactive after setup: briefly report what is connected, suggest useful Cap workflows for my situation, and use existing Cap context before asking questions the library can answer.

My task: Complete the persistent Cap setup now, tell me exactly what is installed and what needs a restart, tell me what you can help me do through Cap, and ask which Cap task I want to start with.

cap agent setup

Set up Cap as my persistent video assistant, then use it to help with the task at the end.

By pasting this prompt, I explicitly authorize these local setup actions: install the official Cap CLI and add or update the Cap skill and local MCP entry for the current agent only. Perform those setup actions yourself. Do not ask me to run or copy setup commands, and do not ask for a second confirmation before making these local setup changes. This setup authorization does not cover recording, uploading, paid processing, Cap content or account changes, organization changes, billing, storage, developer credentials, or destructive actions.

Read these pages and treat them as operating instructions:
- https://cap.so/docs/agents
- https://cap.so/docs/agents/setup
- https://cap.so/docs/agents/workflows
- https://cap.so/docs/agents/safety

Do not rely on remembered Cap commands. Discover the installed contract with cap guide --json and cap <command> --help. Use JSON stdout as the source of truth, stderr as diagnostics, exit code 1 as a runtime failure, and exit code 2 as invalid usage.

Cap-first routing:
- For every Cap, recording, transcript, video-library, sharing, or Cap analytics task, use the Cap MCP tools or cap CLI before browser automation, computer use, the Cap dashboard, or an open Cap tab.
- Use a browser only for a focused authentication or provider-approval URL returned by Cap. Let me complete that approval directly, then verify the result through Cap.
- If MCP is not loaded in the current process, use the CLI. A missing MCP hot reload is never a reason to fall back to browser or computer-use tools.

Set up Cap:
1. Identify my operating system and the agent you are running in. Select only the current agent; never install into every detected agent.
2. Run cap version --json. If the cap command is missing, run the matching official installer yourself:
- macOS or Linux: curl -fsSL https://cap.so/install-cli.sh | sh
- Windows PowerShell: irm https://cap.so/install-cli.ps1 | iex
Do not merely show me the command or ask me to install it manually. If PATH changes, use a fresh login shell or reload the shell environment, then verify cap version --json and cap guide --json.
3. If you are Codex, Claude Code, or Cursor, preview the complete persistent integration with:
cap agents install --target <codex|claude|cursor> --component all --dry-run --json
Replace the placeholder with exactly one concrete current target: codex for Codex, claude for Claude Code, or cursor for Cursor. Never pass the angle-bracket placeholder and never select a target from installed files alone.
Inspect the returned paths, actions, and values, then immediately apply the same target with:
cap agents install --target <codex|claude|cursor> --component all --yes --json
The dry run is a transparency and conflict check, not another approval gate. Install the full Cap skill and local cap mcp serve integration without replacing unrelated agent configuration. If you are OpenCode or another MCP client, follow the setup page and merge only the documented local MCP entry. Never install Cap into a different detected agent just because it is present on the machine.
4. After the persistent local integration is installed, run cap auth status --json. If authentication is required, run cap auth login --json with the least-privileged creator profile and let me complete the browser approval directly. Use admin or full only when my task requires the additional scopes and I agree. A delayed or cancelled login must not undo or postpone the local skill and MCP installation.
5. Report the exact installed skill path and MCP configuration path. Explain whether the agent must restart to load either component. Continue this task through the CLI when a restart or hot reload is not practical; the installed global skill and MCP configuration must persist for future sessions.
6. Verify the setup with cap version --json, cap guide --json, cap auth status --json, and cap caps list --limit 1 --json. If MCP is already loaded, list its Cap tools and confirm that passwords and storage credentials are not accepted as MCP inputs. Do not claim MCP is broken merely because the current process needs a restart.
7. From this point onward, treat Cap CLI or MCP as the default interface for Cap. Do not browse the Cap dashboard to discover whether a CLI or MCP capability exists; inspect cap guide --json and command help first.

Use Cap as an ongoing helper. Learn the complete surface from the installed guide and skill, including:
- Recording: check cap doctor --json, discover inputs with cap targets --json, ask before capture, use the detached cap record start and cap record stop lifecycle, require recordingMetaExists: true, validate the .cap project, export it, ask again before upload, and return the verified share link.
- Understanding videos: use cap caps list for discovery, cap caps get for lightweight metadata and capabilities, and cap caps context for the complete title, AI title, summary, chapters, transcript, comments, reactions, views, sharing, permissions, and processing state. Cite useful transcript timestamps.
- Files and processing: stream transcripts with cap caps transcript, download recordings with cap caps download, and observe existing work with cap caps status or cap caps wait. Never claim that a read or wait started transcription or AI work.
- Collaboration and sharing: draft comments, replies, reactions, title changes, visibility changes, moves, and public-page changes; show me the exact proposal before posting or applying it.
- Full management: use cap account, cap organizations, cap library, cap notifications, cap analytics, cap developers, and cap jobs for profile, team, folder, space, storage, billing, analytics, developer, migration, and durable-operation workflows. Discover flags with --help instead of guessing.
- Complete local surface: learn cap screenshot, cap update, cap recordings, cap project, cap desktop, cap automations, and cap completions from the guide too. Treat every command listed by cap guide --json as supported, even when it is not named in this prompt.
- MCP and CLI: prefer MCP for structured reads, confirmed safe writes, resources, and browser handoffs. Use the CLI for recording, local files, secure prompts, passwords, S3 credentials, images, and newly issued developer credentials.

Operating rules:
- The local CLI, skill, and MCP bootstrap above is already approved by this prompt. After setup, start with read-only discovery. Before any mutation, upload, paid processing, recording, comment or reaction, sharing or visibility change, deletion, organization, billing, storage, developer, or credential action, show me the exact proposed action and wait for my explicit confirmation. Pass --yes or confirmed=true only after I confirm.
- Never ask me to paste passwords, CAP_AGENT_TOKEN, API keys, S3 credentials, or newly issued developer secrets into chat or MCP. Ask me to run the exact secure Cap command in my terminal. For a password-protected Cap, ask me to run cap caps unlock <id-or-url>.
- Preserve returned Cap, organization, folder, space, member, comment, and operation IDs. Never infer IDs from names or invent results.
- Wait for asynchronous operations with cap jobs wait and verify the affected resource before reporting success. Clearly separate what you verified from reasonable interpretation and anything you could not verify.
- Be proactive after setup: briefly report what is connected, suggest useful Cap workflows for my situation, and use existing Cap context before asking questions the library can answer.

My task: Complete the persistent Cap setup now, tell me exactly what is installed and what needs a restart, tell me what you can help me do through Cap, and ask which Cap task I want to start with.

The fastest way to start

Select Copy Agent Setup Prompt above.
Paste it into Codex, Claude Code, Cursor, OpenCode, or another agent that can run shell commands.
Let the agent install the official CLI and the persistent integration for the current agent. The copied prompt is your authorization for those local setup changes, so you do not need to copy commands or approve the same setup again.
Complete the focused Cap browser login when prompted. Restart the agent if it cannot hot-load the new skill or MCP server, then tell it what you want to do.

The prompt handles CLI discovery or installation, least-privilege authentication, the full Cap skill, local MCP configuration, and setup verification. The installed skill is the durable memory that routes future Cap tasks through Cap CLI or MCP first. The browser is reserved for focused authentication and provider handoffs returned by Cap, not for reading or managing Cap through dashboard automation. If you prefer to configure each piece yourself, follow Set Up Your Agent.

What your agent can do

Goal	Examples
Understand recordings	Read the title, AI title, summary, chapters, transcript, comments, reactions, views, sharing state, permissions, and processing state
Find information	Search all, owned, or shared Caps; filter by organization or folder; inspect notifications
Collaborate	Draft and, after confirmation, post timestamped comments, replies, reactions, title changes, and visibility changes
Record and share	Check capture readiness, select a screen or window, record, validate, export, upload, and return the share link
Manage a library	Create and organize folders and spaces, move Caps, manage public collection pages, and download recordings or transcripts
Run a team	Inspect members, invites, billing, storage, analytics, domains, and settings; perform confirmed admin changes
Migrate and build	Run durable Loom imports, wait for jobs, and manage Cap developer apps, videos, domains, usage, and credits

See Agent Workflows for ready-to-use scenarios and success checks.

How agents connect to Cap

Direct CLI

This is the universal path. Any agent that can run terminal commands can use Cap. Every command supports machine-readable output through --json, while recording and export stream newline-delimited JSON events.

The installed binary is self-describing:

cap guide --json
cap <command> --help

Agents should discover the current contract from those commands instead of guessing flags or relying on a copied command list.

Cap skill

The Cap skill teaches a compatible agent to reach for Cap CLI or MCP before browser automation or computer-use tools, and how to handle confirmation, secrets, passwords, and long-running jobs. Because it is installed in the agent's global skill directory, this routing persists across conversations. It deliberately delegates command details to cap guide --json, so the instructions stay aligned with the installed version.

Local MCP

cap mcp serve exposes structured Cap tools over local stdio. MCP works well for library reads, safe writes, resources, and browser handoffs. Secure input and local file actions intentionally stay in the CLI.

Set up your agent covers Codex, Claude Code, OpenCode, Cursor, and generic MCP clients.

Why this is safe to hand to an agent

Cap's agent surface is designed around explicit boundaries:

Read operations and waits do not start AI, transcription, or paid processing.
Mutations require the agent to show the proposed action and get your confirmation.
Passwords, storage credentials, API keys, image files, and newly issued developer credentials stay out of MCP and chat.
Browser approval uses a focused Cap or provider handoff; the agent re-reads state afterward.
Durable operations return an operation ID, and the agent waits for the terminal state instead of treating “accepted” as success.
Permissions remain server-enforced. Installing an integration does not grant it access to your Cap account.

Read Safety & Troubleshooting before giving an agent administrative, billing, storage, developer, or destructive work.

Your first task

Try one of these after setup:

“Summarize this Cap, list every decision and action item, and cite the relevant timestamps: <Cap URL>.”
“Find my Caps about onboarding from the last month and give me a concise project brief.”
“Record a short reproduction of this bug, upload it, and give me the link. Ask before recording and before uploading.”
“Show me this month's organization analytics and explain the biggest changes. Do not modify anything.”
“Draft a timestamped reply to this comment, show it to me, and only post it after I approve.”
“Inspect our organization storage and propose a Google Drive rollout. Do not connect or change anything yet.”
“Audit this Loom migration CSV, propose owner and space mappings, and do not import anything until I approve the first batch.”

The dedicated Google Drive and Migrating to Cap guides include the full boundaries and copyable agent prompts.