Linear Cycle Progress Digest with Claude Code
The hard instruction here is a refusal: report the age of work that has gone quiet and say nothing whatever about why. No burndown nobody handed it, no forecast about whether the cycle lands, no blending of pointed and unpointed work into a single number. Claude Code holds long structured output steady, and the structure in this case is largely a list of things it must not compute.
Watch it work before it's live
Run a staged conversation — no account needed. The agent handles it for real while a simulated world answers its tool calls; nothing touches real accounts, and nothing is actually sent.
Cycle day 4
Two week cycle, 38 issues in scope, 7 completed and 14 in progress. On day 4 of Cycle 30 this same team had 11 completed. Three issues have been in progress since the cycle opened, all of them assigned to the engineer who is also on call this week. The team sets no estimates on anything.
Set up in minutes
Using this template drops you into a guided setup. It asks exactly this, nothing else:
Connect Linear
One sign-in. The agent acts through your account, scoped to what this template uses.
Connect Slack
One sign-in. The agent acts through your account, scoped to what this template uses.
Team scope
Which Linear team this covers, how many days a piece of work may sit in progress before you want it named out loud, and who to tag when Linear hands back nothing.
Digest style
How the read should land: bare numbers or numbers with a line of context, how many issues you want listed under each heading, and how blunt the sitting section is allowed to be.
Runs on Claude Code
Preselected for this page — connect your Claude Code account during setup, or switch to NoClick's built-in models with one click.
Watch it handle a test run
A staged conversation against a simulated world — then it’s live.
Why Claude Code for this agent
Ages reported, causes left alone
An issue sitting nine days with a named owner starts the right conversation. The same line with a guess attached starts a different and much worse one in a public channel.
Counts labelled as counts
Where a team leaves estimates empty it counts issues and says on the line that these are issue counts, so nothing arrives looking like velocity that is not.
Before you fork
Half our teams estimate and half do not. One template or two?
One fork per team, each carrying its own team scope. A team with estimates empty gets issue counts labelled as counts, and a team that points gets the same headings computed from its own estimate field. What never happens is a single figure that quietly mixes estimated and unestimated work together.
Run it with a different agent
Put Linear Cycle Progress Digest to work on Claude Code
Free to start. Guided setup, a test run against staged conversations, and it's live.