Agent Team template
A code review workflow that watches pull requests, assigns specialist reviewers, checks implementation risk, and posts concise review notes with links to evidence.
One-message setup · 3 specialists · Live after setup
Designed for
AI startups and small product teams that need faster PR review without weakening engineering judgment
Outcome
Review every pull request for architecture risk, test gaps, security concerns, and deploy readiness before merge.
Say what should be true when the work is done.
Codelit runs one labeled Sample with no account, model, or external App calls.
Review the evidence, then reuse the same brief with your data when it is useful.
Summarizes the PR and detects changed system boundaries.
Fast tool-use model
Looks for boundary, coupling, and production-readiness issues.
Deep reasoning model
Checks sensitive paths, auth changes, dependency risk, and secrets.
Policy-focused reasoning model
Loads the workflow goal, allowed actions, escalation policy, and output contract before the agent plans work.
A review skill for architecture risk, test gaps, secrets, migrations, and deploy readiness.
Centralizes high-risk action checks for writes, secrets, customer data, billing, deploys, and public communications.
Exposes pull request diffs, CI status, file reads, review drafts, and CODEOWNER metadata.
tools · resources · prompts
Read the diff and produce a system-level summary.
Check changed boundaries, new coupling, data migrations, and missing docs.
Inspect auth, secrets, permissions, and dependency changes.
Combine findings into a concise review with evidence links and test suggestions.
Open it in Codelit and describe the result. Codelit handles common setup while Flow stays available for direct editing and Activity keeps the proof.
Use this teamTurns one scoped release request into a reviewed branch artifact, preview deployment, browser-verified result, pull request, production promotion, and Slack proof using the accounts the team already owns.
Correlates Sentry, Datadog, PagerDuty, and deployment evidence, proposes one bounded mitigation, pauses on the exact actions, and leaves status proof for responders.
A Devin-style engineering workflow that turns a scoped ticket into a branch, implementation plan, code changes, test run, and pull request draft with review evidence.