Agents and Chat
ffgit works with the coding agents you already have: it starts the installed Claude Code and Codex CLIs, signed in with your own account. ffgit does not provide a model or resell tokens.
Start an agent task
Section titled “Start an agent task”Choose Agents → Start agent task…. A new chat opens in Chat.
Pick Claude Code or Codex, the model, and whether it works in this worktree or a new one. Templates fill the task with one of twelve ready-made prompts — such as a review that leaves
git statusas it is — or with your own.Start it. ⌘↩ starts it and keeps the form open, so the same task can go to another agent or model, each in a new worktree with the next free name.
A new worktree for an agent can first run the project’s worktree setup: copy ignored files from the main checkout, run commands and check paths. It runs only after you reviewed every step, and the agent starts once it is done.
Each run gets ffgit’s MCP tools for that session. ffgit follows whether the run is alive, how it ended, how many files its worktree has changed and how many commits its HEAD gained.
Live status
Section titled “Live status”For Claude Code, ffgit reads the status file Claude Code keeps for each running session (~/.claude/sessions/<pid>.json): working, waiting for permission or input, idle, or a response ready after a turn. A run started from ffgit also says what it waits for — Needs permission, Asking a question, Waiting for you, Rate limited, Error and more — from session-only hooks that are never written to your settings files.
Agents and Activity
Section titled “Agents and Activity”Agents has two tabs:
- Sessions — ffgit’s runs, live Claude Code sessions and discovered Codex and Claude Code sessions in one list or board: Needs you, Working, Ready, Errors, Idle.
- Activity — one inbox for questions, ready responses and failures, with Needs you, Ready for review, Errors and All activity views. The rail and header count unread threads.
The sidebar shows agents inside the project tree: status counts on each project, a glyph on each worktree and up to three agent rows under it.
Chat lists the project’s chats. Opening one shows its conversation, read from the agent’s own transcript on this Mac: messages, tool calls folded with their results, reasoning on request and new lines as they arrive.
Agents started with Start agent task… or Resume in ffgit run in a terminal in Chat, where you type to answer them. ⌘F finds text in it, scrollback included.
Storage
Section titled “Storage”A session’s detail shows everything its chat keeps on this Mac — the conversation, scratchpad and task output, images and plans — split into what can be freed (it is written again by the next run) and what is kept. The Agents list shows each chat’s size with totals per project.