Permission prompts#
When an agent requests permission for a tool call, file edit, or command, AgentPeek opens the prompt inline, with the command, file path, or diff laid out so you can decide fast. Keyboard actions stay close:
A Deny with feedback option lets you send a note back when the agent accepts one. AgentPeek sends a response only after you choose an action.
Which agents can be answered#
In-notch answers work for Claude Code, Codex, Qoder, CodeBuddy, Gajae Code Direct Chat, OpenCode, MiMo Code, GitHub Copilot, Kilo Code, Factory Droid, Antigravity, Qwen Code, Pi, Oh My Pi Direct Chat, Cline, Goose Direct Chat, Kiro Direct Chat, Mistral Vibe Direct Chat, and Devin. Cursor, Grok Build, Kimi Code, Hermes, Oh My Pi, and ZCode prompts are observation-only. Approvals stay in the native agent, so AgentPeek flags the waiting session and ⌥ T takes you there. Antigravity, Factory Droid, and Qoder answer only the mutating tools their hooks hold; reads, and any request that arrives while AgentPeek is unavailable, return to the agent's own permission flow.
Each agent's own page under Supported agents documents its exact prompt boundaries, including the cases where a Direct Chat session can answer native permissions while ambient terminal approvals stay in the agent.
Command Code checks native permissions before its PreToolUse observer, so AgentPeek receives neither a waiting prompt nor a decision channel from that hook. The monitored session remains visible, and Open Terminal returns to the Command Code surface that owns the decision.
Questions#
When an agent asks a question, AgentPeek shows the title, detail, and any options. Click an option to answer, or type a custom response and press Return when the agent allows one. For a multi-part question, each card carries its own choices, single or multi-select, with a Send button that lights up once you've answered them all. Use ← / → to move between pending prompts, or hand any one back with Answer in terminal.
Plans#
For a plan the buttons read Approve and Reject, and Reject with feedback lets you send a note back explaining what to change. An adopted plan stays visible on the session card as a collapsible checklist while the agent works through it.
Keeping approvals in the terminal#
Prefer to keep approvals in the terminal? Set Settings then Notch then Prompt handling to App / CLI, or set global hotkeys in Settings then Shortcuts to allow or deny the frontmost prompt without opening AgentPeek at all. Every prompt and answer also lands in the session timeline, next to the usage numbers and tool calls it belongs with.