Devin Session Review Agent with Claude Code
Reviewing a Devin session means reading a record another agent produced: the task it was handed, the trail it left, the artifacts it claims, and whether its own summary and those artifacts actually agree. Where they disagree, both get reported and labelled. Claude Code goes through context in full before it settles on a view, which is the entire requirement when the subject is an AI's account of its own work.
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.
Migrate the notifications service off Moment.js to date-fns
Ran 47 minutes. Opened pull request 318 in fleetwing/notifications across 61 files, CI green. The session summary calls the migration complete, while a later message notes one helper, the business day offset used by the digest scheduler, still calls Moment because date-fns carries no direct equivalent. The run ended with the pull request left as a draft.
Set up in minutes
Using this template drops you into a guided setup. It asks exactly this, nothing else:
Connect Devin
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.
Review rules
What finished actually means to you: what a session has to produce before you would call it shipped, the shortcuts you refuse to accept as a fix, whether the agent may message a stalled session back, and who owns the queue when one goes wrong.
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
An account, not a result
A closing summary is a claim made by the thing being reviewed. Treating it as one input among several, rather than as the answer, is the difference between a digest and an echo.
Both versions when they differ
Session says complete, artifacts say draft pull request with one helper still unmigrated. The template reports both and says which is which, instead of picking the tidier one.
Before you fork
What stops it calling something SHIPPED when there is no link?
SHIPPED requires a pull request or artifact link present in the session data, and everything without one falls to PARTIAL, STALLED or NEEDS INPUT. A harness that reads the record properly is what makes that rule bite, because the pull is always towards trusting a confident sign off. Watch it against the Test Run where a session ends tidily with nothing attached.
Run it with a different agent
Put Devin Session Review Agent to work on Claude Code
Free to start. Guided setup, a test run against staged conversations, and it's live.