Get started

How we run async standups in Slack

A daily agent that collects each person's Linear and GitHub activity, prompts anyone with nothing recorded, and posts a concise team standup to Slack. Read-only across every tool.

Slack
Linear
GitHub
Written by
The OpenChatly Team
Published
January 28, 2026
Reading time
7 min read
Topics
Operations, Case Study, Team

A standup is supposed to answer one question: what did everyone do, and what's next. In practice it costs a meeting, or a thread where half the team pastes a summary and the other half forgets. The information already exists in Linear and GitHub; someone just has to gather it, format it, and chase the people who didn't post.

We run a daily agent on Kortix that does the gathering. It reads each person's Linear and GitHub activity, nudges anyone with nothing recorded, and posts a concise standup to a Slack channel. This is how we run our own standups, and the same setup works for any team.

Team
Kortix
Runs on
A daily cron, one post per weekday
Connected systems
Linear · GitHub · Slack
Mode
Read-only across the tools, no writes

The problem

A live standup takes a slot on everyone's calendar to relay information that's already recorded somewhere. An async thread saves the meeting but shifts the work onto people: each person has to remember to write, summarize their own day, and post it, and the ones who don't leave gaps.

The common workarounds are partial. A recurring bot that asks "what did you do yesterday?" still depends on everyone answering. A dashboard shows activity but doesn't summarize it or tell you who's quiet. Neither reads the tools where the work actually happened, so the summary is only as complete as the people filling it in.

What we built

On Kortix, a cron fires once each weekday morning and spawns an agent. It reads each team member's recent Linear issues and GitHub activity, builds a short per-person summary, checks who has nothing recorded, and posts the standup to a Slack channel. Anyone with a quiet day gets a light prompt so they can add context the tools can't see. The agent only reads; it never writes to Linear or GitHub.

How it works

1

Copy the setup prompt into a new session

Open your Kortix workspace, start a new session, paste this prompt and send it. The agent writes the agent file, the leaderboard skill and the weekly trigger, and opens a change request for you to review. Prefer clicks? Choose Use this template instead.

Setup prompt

Set up a weekly shipping brief agent in this workspace.

  1. Create the agent agents/leaderboard.md. Its job is to post a weekly shipping brief to Slack and open the async standup thread. It may use the GH_TOKEN secret and the Slack channel.

  2. Create the skill skills/weekly-leaderboard/SKILL.md with these rules:

    • Cover the last 7 days, or the time since the last brief in #eng, so nothing counts twice.
    • Count merged pull requests per person across owner/repo with gh. Leave out bots and agents, and count them on a separate line.
    • Compare each count to last week in memory/weekly-digests.md, and track streaks of weeks with at least one merged pull request.
    • Post one brief to #eng: a one-line takeaway, what shipped, the ranked leaderboard, streaks and decisions from Slack.
    • Reply in the brief's thread with the standup prompt (what shipped, top priority, blockers) and mention @here.
    • Add this week to memory/weekly-digests.md and keep the last 8 weeks.
  3. Add a cron trigger weekly-leaderboard to kortix.yaml. It runs the leaderboard agent every Monday at 09:00 with the prompt "Load the weekly-leaderboard skill and post this week's shipping brief and standup thread to #eng."

  4. Tell me which of these connectors and secrets are not set up yet.

  5. Open a change request with all of it. Do not merge it.

2

Connect your tools

Add a GitHub token as a workspace secret, and connect Slack as a channel so the agent can post the brief and the standup thread. The token is encrypted and injected into the session at runtime, scoped to this agent.

GitHub

Counts merged PRs per person across the target repos.

Or useLinearJira
Required
Slack

Posts the weekly brief and opens the standup thread.

Or useMicrosoft Teams
Required
3

Run it once with this prompt

Merge the change request, then start a session with the leaderboard agent and send this prompt. Check the counts against GitHub before you let the schedule take over.

Prompt

Post this week's shipping brief to #eng.

  1. Count merged pull requests per person in owner/repo over the last 7 days. Leave out bots and agents, and count them on one separate line.
  2. Compare each count to last week in memory/weekly-digests.md, and work out each streak.
  3. Post one brief to #eng: a one-line takeaway, what shipped, the ranked leaderboard, streaks and any decisions from Slack.
  4. Reply in that thread with the async standup prompt and mention @here.
  5. Add this week to memory/weekly-digests.md.
4

Let the weekly schedule take over

The change request added this trigger to kortix.yaml. From now on the agent runs every Monday at 09:00. It reads last week's entry in memory before it counts, so deltas and streaks carry from week to week. To change the time, edit the cron line, or open Triggers in the workspace.

kortix.yaml
triggers:- slug: weekly-leaderboard  name: Weekly leaderboard  on:    cron: "0 0 9 * * 1"  run:    agent: leaderboard    prompt: Load the weekly-leaderboard skill and post this week's shipping brief and standup thread to #eng.
5

Count only what GitHub shows

Every count, delta and streak traces to gh pr list output. Bot and agent pull requests are listed apart, and a pull request a person drove counts for that person even when an agent helped write it. The agent posts one brief per run and pastes no tokens or customer data.

6

Read the weekly brief

Each run ends with one brief in #eng and a standup thread under it. This is what a run looks like in the session:

Weekly leaderboard · Mon 09:00
Load the weekly-leaderboard skill and post this week's shipping brief and standup thread to #eng.
Worked for 3m 26s
github · gh pr list (merged)github · list commitsslack · read history → #engslack · send blocks → #engslack · reply in threadmemory · update weekly-digests.md

42 pull requests merged by 9 people this week, plus 11 from bots. The top shipper merged 8, and 3 people extended a streak past four weeks. The standup thread is open in #eng.

Illustrative example. Your counts depend on your repos.

The pattern

A cron trigger spawns a session each morning with read-only connectors into Linear and GitHub. The roster and format live as skills and memory. The agent summarizes, prompts the gaps, and posts to Slack, its only write.

Make it do more

Once it works, paste any of these into the same session.

Summarize the standup replies

Every Tuesday at 10:00, read the replies in this week's standup thread and post a five-line summary of priorities and blockers to #eng.

Name the slow reviews

Add a line to the brief that lists pull requests that waited more than 2 days for a first review this week.

Show names, not logins

Here is our list of GitHub logins and names. Add it to the skill's identity map so the leaderboard shows names.

Guardrails

The agent reads everyone's activity across two tools and posts to a shared channel, so the access is scoped and contained:

  • Isolation. Every run happens in its own isolated sandbox. The session reads the day's activity, builds the summary, and only the Slack post is written back out.
  • Scoped secrets. The Linear, GitHub, and Slack credentials are encrypted in the Secrets Manager and injected into the sandbox at runtime, scoped to the agents you grant them to.
  • Read-only across the tools. The Linear and GitHub connectors are scoped to read. The agent's only write is the standup post; it changes nothing in the source tools.
  • Everything is code. The roster, the format, and the per-tool permissions are files in the repo, versioned and changed through a reviewed change request rather than a dashboard setting.

The outcome

The standup is a post, not a slot on the calendar
No meeting
No writes to Linear or GitHub, only the Slack post
Read-only
Linear, GitHub, and Slack in one daily agent
3 systems

The standup now arrives each morning as a Slack post built from the work people already recorded, with quiet days flagged instead of skipped. No one spends a meeting relaying status, and no one has to write their own summary for the activity the tools already have.

On this page

  • The problem
  • What we built
  • How it works
  • Make it do more
  • Guardrails
  • The outcome

Run this yourself

Install this exact setup — agent, connectors, schedule, and guardrails — in a guided flow.

More use cases.

  • How we handle GDPR data-subject requests on a deadline

    Legal·July 11, 2026

  • OpenChatly

    How we keep our docs in sync with the code

    Documentation·July 5, 2026

  • OpenChatly

    How we QA every pull request automatically

    QA·July 5, 2026

Own your AI.Start today, in our cloud.

Start for free

OpenChatly is the AI workspace for everything. One person directing, agents executing, from goal to finished work.

©2026 OpenChatly AI.沪ICP备2025124785号-5

Resource guide

  • Product overview
  • Skills marketplace

Terms of service

  • User agreement
  • Privacy policy

Contact us