Weekly Changelog Agent
Turns the week's merged pull requests into one readable Friday changelog in Slack, authors credited, pull requests linked, and nothing invented about what a change does.
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.
Friday 15:00 changelog tick
It is Friday 15:00 in Berlin. Twenty three pull requests merged across the api and dashboard repos this week, including one that renames a field in the settlement webhook payload and one that removes a reporting endpoint two customers still call. The audience is support and the twelve merchants on the beta.
Set up in minutes
Using this template drops you into a guided setup. It asks exactly this, nothing else:
Connect GitHub
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.
Repo context
Which repositories to cover, who reads this changelog (customers, support, the whole company), and who to tag when a repository goes silent or a call fails.
Changelog style
How your changelog should read: how technical to get, whether dependency bumps and internal refactors make the cut, and how long it can run before people skim.
Choose which agent runs it
NoClick's built-in models work out of the box — or bring Claude Code, Codex, and other coding agents on your own subscription.
Watch it handle a test run
A staged conversation against a simulated world — then it’s live.
About this agent
Changelogs get written the week somebody has time, which is never the week things shipped. Every Friday afternoon this agent reads the pull requests merged since Monday and writes the week in plain language: what shipped, what got fixed, what breaks, and who did it. It holds up because it describes each change from the pull request itself and lists anything it cannot describe rather than filling the gap with a guess.
What people use it for
- Tell support what shipped - Support finds out about a change from a confused customer more often than from engineering. One Friday message in plain language means they read it before Monday's tickets arrive.
- Surface undocumented breaking changes - Anything that removes or renames something lands in BREAKING with the migration note quoted, or with a line saying the author never wrote one. That question gets asked while the author is still around.
- Stop writing release notes by hand - The raw material is already in your pull request titles and bodies. This turns that into a written changelog every week without anyone opening the compare view on a Friday evening.
- Give the company a Friday read - Non engineers get one message they can actually follow, with authors credited by handle. It is the cheapest way to make a quiet infrastructure week visible to the people funding it.
Before you fork
What does it need connected?
A GitHub credential with read access to the repositories you want covered, and one Slack channel to post in. During setup you name the repos, the audience, and the style you want. It only reads from GitHub and never comments, tags, publishes a release, or pushes anything.
What does it cost to run?
One run a week per workflow, whether your team merged four pull requests or forty. The run reads the week's merges and posts a single message, so cost tracks the schedule rather than your repo size. Teams that ship daily sometimes move it to twice a week, which doubles it.
What if it describes a change wrongly?
It writes only from the pull request title, body and linked issue, so a wrong line usually means a pull request described itself badly, which is worth knowing. A merge with no usable description goes into INTERNAL marked description unclear instead of being narrated. You can rehearse it on the staged weeks before pointing it at your real repos.
Run it with your coding agent
More agents like this
Put Weekly Changelog Agent to work
Free to start. Guided setup, a test run against staged conversations, and it's live.