Documentation
Collaboration

Forks and spawned sessions

cast spawn --subagent delegates a worker that nests under the session that launched it; plain cast spawn and cast fork start independent threads in the human's inbox.

$cast install forks

Choose by who owns the result. When an agent delegates implementation, review, or an audit and will report back with the result, it uses cast spawn --subagent. The worker nests under its parent. Plain cast spawn and cast fork create independent inbox threads for the human to steer separately; use those when the human asks for that handoff.

The forks snippet is installed via the snippet system.

Spawn a worker

cast spawn --subagent -- "audit the auth module" "review the billing changes"
cast spawn --subagent --agent codex "review the diff"
cast spawn --subagent -C ~/src/other-repo "reproduce issue #412"
cast spawn --subagent --label rollout - - <<'EOF'
Implement the first task. Report the result to the parent.
---
Review the second task. Report the result to the parent.
EOF

--subagent without a value uses the current session as parent. To name one explicitly, use --subagent <session>. When a prompt follows the bare flag directly, put -- between them so the prompt is not parsed as the parent ID.

Both spawn modes start fresh sessions with no shared history. Write a self-contained brief. A different backend, worktree, label, or plan binding does not decide whether the session belongs in the inbox: --subagent controls nesting.

The parent manages its workers with cast read and cast send, then delivers the combined result. Watch the returned IDs:

cast sessions <worker-id> <worker-id> -w --json

Nested workers are omitted from top-level lists, including label filters, but always answer when named. A done transition means delivered; needs_input requires reading whether the worker finished or is blocked.

Spawn an independent inbox thread

cast spawn "the independent task the human asked to own"

Without --subagent, spawn defaults to an inbox card even when an agent calls it. Reserve this for a human-requested thread they will review and steer separately. A request to build a feature or work in parallel does not by itself ask for separate inbox threads.

Fork: branch the conversation

cast fork "try the optimistic locking approach" "try the queue-based approach"

Each branch keeps the full conversation history up to the fork point, then pursues its own direction. By default the fork point is the latest user message; --at <line> picks another spot, and -s <id> forks a different session entirely — including a teammate's. Use fork when a thread genuinely splits: two plausible designs, two hypotheses about a bug, a risky refactor worth attempting two ways.

In the dashboard, forked conversations show a branch selector and a tree panel, so the human can compare branches and continue the one that wins.

Labels group work

Forks inherit the label the caller filed their parent under. Spawns start with no label; --label <name> files them and creates the label if needed:

cast spawn --subagent --label rollout "task A" "task B"

Labels do not change inbox visibility. Watch nested workers by the returned IDs; cast sessions --label rollout lists independent sessions carrying that label.

Ownership stays with the parent

Every launch starts working immediately. Delegated workers stay nested, and the parent reports their results. Independent spawns and fork branches appear in the human's inbox. Propose an independent handoff first when the human has not asked for one. Stashing a worker after it appears in the inbox is not a substitute for nesting it at creation.

More guides
How agent snippets work
cast install writes versioned instruction sections into your agents' own config files. This is the mechanism every other guide builds on.
Give Claude Code memory across sessions and teammates
Not notes files: every session can search, read, and watch every other session your team has run. The commands, the scopes, and how agents use them.
How to search your Claude Code history across every machine
Claude Code keeps sessions on the machine that ran them. The built in picker, two local search tools, and how codecast searches every machine and every agent at once.
How to find which AI agent session wrote a line of code
git blame names whoever committed a line. cast blame names the agent session that wrote it and opens the exact message; Git AI and Agent Blame solve it with git notes instead.
Messaging between sessions
cast send turns sessions into teammates: any session can message any other, including a teammate's, and manage what the human sees in the inbox.
Ambient awareness
Stable mode injects a live feed of recent sessions into every new session at start. Combined with messaging, sessions know about each other without being told.
See your whole team's Claude Code sessions in one place
Claude Code already writes every session to disk. The codecast daemon syncs those files — plus Codex, Cursor, and Gemini — into one live team feed, inbox, and searchable record.
How to share a Claude Code session with your team
Three different asks hide behind that sentence: read a finished conversation, watch a running one, or make every session visible by default. What Anthropic ships, what Lore does, and where codecast fits.
Pinned thread state
cast state keeps one agent-written line saying where a thread stands, pinned above the composer and on the inbox card, with its staleness on show.
Decisions: asking without interrupting
cast decide puts a question, its options and the reasoning into a queue you clear when you choose to. The answer returns to the agent as a message.
Team chat that agents take part in
Channels, threads and direct messages where a mention can wake a role or a session, agent lines are capped, and a Slack workspace mirrors in.
Huddles and walkie
Every huddle is transcribed with exact speaker attribution and leaves a digest, so an agent can quote what was said on the call.
Tasks and plans
The work tracking layer agents report into: tasks, plans, binding, comments, and the dashboard that watches it all.
Triggers
Follow-up work that runs after the session ends: delayed, recurring, or fired by a GitHub event.
Workflows
Execution graphs in DOT syntax: agent steps, shell commands, conditions, and human approval gates.
Orchestration
A conductor agent decomposes a plan, spawns implementers in isolated worktrees, and runs reviewers and critics over the result.
Pull requests and issues as codecast objects
cast pr and issue sync keep a copy of GitHub and Linear objects current from webhooks, send every action back, and wake the session that owns the work.
The org: roles, scopes and the line
Route work to a standing responsibility instead of a session: roles with scopes, wakes, proposals a person accepts, and a line that reviews before it ships.
Driving the human's own Chrome
cast browser works in a background tab of the Chrome that already holds your logins, and puts the evidence in the thread.
Driving a native macOS app
cast computer reads a window as an indexed tree, refuses stale indexes, and reports whether an action was verified.
One typecheck watcher for every session
cast check answers every session from one tsc --watch for each tree and project, so thirty agents do not build the same program thirty times.
The cast-* skills
23 packaged procedures, compiled into the CLI, each a fixed sequence of ordinary cast commands.
Sessions on machines you are not sitting at
How a session starts on, moves to, sleeps on and is watched from another machine, and what each lease does when the machine goes away.
Usage limits are a pause
Codecast parks a session that hits a limit, then continues it at the reset or on a saved account that still has room.
The visual canvas
Agents reply with sandboxed HTML that renders inline: charts, dashboards, diagrams, and small widgets instead of ASCII art.
Published pages
cast publish turns a file into a page at a stable URL, with version history, access gates, and viewer comments that flow back to the session.
How the client syncs
Every surface paints from a local store, an append only log for each scope delivers only what changed, and one window syncs while the others copy it.