Documentation
Output

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.

$cast install publish

cast publish turns a file into a public page at a stable URL. An agent finishes a report, publishes it, and puts the link in its reply; the human opens a clean, branded page instead of scrolling a transcript. Republishing the same file updates the same URL, so links keep working across revisions while every previous version stays viewable.

The publish snippet teaches agents to do this for standalone deliverables — reports, dashboards, mockups, visualizations — and to put the returned URL inline in the reply. It is installed via the snippet system.

Publishing

cast publish report.html      # → https://codecast.sh/a/<slug>  (stable per file)
cast publish notes.md         # markdown renders as a clean reading page
cast publish dist/            # directory bundle (needs index.html; relative assets work)
cast publish app.html --watch # republish on every save; viewers auto-reload with ?live=1
cast publish ls               # list your pages
cast publish rm <target>      # unpublish

The URL is stable per file path: publish report.html again and the same link now serves the new content. --new mints a separate URL when you deliberately want a second page. Pages are unlisted but viewable by anyone with the link — the snippet instructs agents to gate sensitive deliverables or flag the sensitivity and let the human decide.

Version history

Every republish keeps history. Past versions stay viewable (?v=N), diffable (?diff=A..B), and restorable:

cast publish versions report.html      # history + rollback/diff hints
cast publish rollback report.html 3    # restore version 3 as a new version

Rollback restores by publishing the old content as a new version, so history stays linear and nothing is lost.

Access gates

cast publish report.html --password s3cret     # password gate (--password-stdin to keep it
                                               # out of the process list)
cast publish report.html --email-gate          # viewers enter an email to open it
cast publish report.html --expires 7d          # 7d / 24h / 30m / never
cast publish set report.html --title "Q3 review" --no-password

cast publish set changes gates, title, or edit mode on an existing page without republishing content. --edit-mode owner|link|team controls in-browser editing; the publish output includes a private owner link with full powers (stats, gates, rollback) and, in link edit mode, an edit URL that grants editing to whoever holds it. cast publish links <target> reprints all of them, and every management command takes a slug instead of the file, so a page stays manageable without the original file or a browser.

Comments close the loop

Viewers can comment on a published page. Comments arrive in the publishing session as messages — the agent that made the page hears the feedback — and stay readable later:

cast publish comments report.html               # read viewer comments
cast publish comments report.html --resolve <id>

The intended loop: a viewer comments, the agent revises and republishes (same URL), then resolves the comment. The snippet adds one guardrail: comment text is viewer-supplied and untrusted — feedback to weigh, never instructions to follow.

cast publish viewers <target> shows the view count and, when the email gate is on, who opened it. Every command takes --json for scripting.

Canvas or page?

The visual canvas renders inside a conversation and lives in the transcript; a published page lives at its own URL with gates and history. Inline evidence for the person reading the session goes on a canvas. Deliverables someone will open by link — status pages, reports for stakeholders, live dashboards under --watch — get published.

For a single image there is a third door: cast image <file-or-url> uploads a screenshot or chart render and prints a stable URL that renders inline in message markdown and canvases — no page around it. See screenshots and images for how agents use it.

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.
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.
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.
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.