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 complete video assistant, then use it to help with the task at the end.

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.

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, show me the exact platform install command and what it changes, then wait for my confirmation before running it:
   - macOS or Linux: curl -fsSL https://cap.so/install-cli.sh | sh
   - Windows PowerShell: irm https://cap.so/install-cli.ps1 | iex
   Open a new shell if PATH changes, then verify cap version --json and cap guide --json.
3. 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.
4. If you are Codex, Claude Code, or Cursor, preview the complete integration with:
   cap agents install --target <codex|claude|cursor> --component all --dry-run --json
   Show me the exact skill and MCP configuration paths and values. After I approve, apply the same command with --yes instead of --dry-run. This must install the full Cap skill and the 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.
5. Tell me if the agent must restart to load the new skill or MCP server. Continue the current task through the CLI when a restart is not practical.
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 loaded, list its Cap tools and confirm that passwords and storage credentials are not accepted as MCP inputs.

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:
- 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: Set up Cap completely, tell me what you can now help me do, and ask which Cap task I want to start with.

cap agent setup

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

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.

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, show me the exact platform install command and what it changes, then wait for my confirmation before running it:
- macOS or Linux: curl -fsSL https://cap.so/install-cli.sh | sh
- Windows PowerShell: irm https://cap.so/install-cli.ps1 | iex
Open a new shell if PATH changes, then verify cap version --json and cap guide --json.
3. 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.
4. If you are Codex, Claude Code, or Cursor, preview the complete integration with:
cap agents install --target <codex|claude|cursor> --component all --dry-run --json
Show me the exact skill and MCP configuration paths and values. After I approve, apply the same command with --yes instead of --dry-run. This must install the full Cap skill and the 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.
5. Tell me if the agent must restart to load the new skill or MCP server. Continue the current task through the CLI when a restart is not practical.
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 loaded, list its Cap tools and confirm that passwords and storage credentials are not accepted as MCP inputs.

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:
- 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: Set up Cap completely, tell me what you can now help me do, 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.
Review the exact CLI and agent-configuration changes it proposes, then approve them.
Complete the focused Cap browser login when prompted and tell the agent 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. It then teaches the agent to use Cap as an ongoing recording, video-understanding, collaboration, and organization helper. 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 when to reach for Cap and how to handle confirmation, secrets, passwords, and long-running jobs. 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.