Available nowShipped, and it works on a fresh install with the default settings.

Live dashboards over your plans, in files you own.

Your team's view of the sprint isn't Jira's, and it isn't GitHub's.

Start from the ready-made sprint analysis and kickoff console, or write the page you want, such as blocked stories with their PRs and tickets: an HTML page that reads your plans and your agents’ routine results.

Your agents fetch outside data with their own tools and publish it as a routine result. The page reads that result and never sees a token.

It's a file in your team's context repo, versioned in git like the rest of it.

How it goes

From the moment it starts to done. Each flow carries its own label.

Open a ready-made one

Available now
  1. Copy Copy sprint analysis or the kickoff console from the CodeSense docs’ examples.
  2. Open Open it in your team.
  3. Done It reads your stories live.

A dashboard is an HTML file in your context that reads your stories.

File blocked-stories.html HTML
<meta name="cs:type" content="dashboard">
<h2>Blocked stories</h2>
<ul id="blocked"></ul>
<script type="module">
// In a trusted workspace, reads need no grant.
if (window.codesense) {
  const res = await window.codesense
    .queryContext({ where: { kinds: ["story"] }, match: { status: "blocked" } })
    .catch(() => null);
  document.getElementById("blocked").replaceChildren(
    ...(res?.rows ?? []).map((d) => Object.assign(document.createElement("li"), { textContent: d.id })),
  );
}
</script>

What's real today

What ships, what needs setup, and what isn't built yet.

Available now Works today

  • Ready-made example dashboards come with the CodeSense docs: a sprint analysis page and a kickoff console. Copy one into your team and it runs live over your stories.
  • Any .html file in your context is a live page. It renders beside your plans, reads them through a small page SDK, and is versioned in your git like everything else.
  • Any HTML page in your context becomes a live view of your stories and your agents’ routine results.
  • Every verb runs when the page calls it, with no grant or confirm dialog. Runaway guards cap bulk writes and chat bursts, and each action is recorded in a local log.

Coming Not built yet

Read more

Try it on your own repos, with your own agents.