Quickstart
Set up Cloud Agents for a repository, configure safety, and launch your first review and execute runs.
This guide gets a repository from zero to its first two useful workflows:
- a review run that inspects an incoming change, and
- an execute run that prepares a scoped code change under approval.
Prerequisites
- A Skytells account
- Pro plan or higher — see Account Plans
- A GitHub repository you are authorized to connect
- A repository owner who can decide approval and protected-path policy
Cloud Agents relies on the Console's GitHub connection model. If GitHub is not connected yet, complete GitHub Integration first, then return here.
Before You Turn It On
Before a repository is connected, decide a few things explicitly.
| Decision | Why it matters |
|---|---|
| Who owns repository policy | Someone needs authority to decide what is protected, ignored, or eligible for automation. |
| Who approves sensitive outputs | Approval queues fail quickly when the product is configured but nobody owns the decision. |
| Which branch flow matters | Runs are only useful if they operate on the same branch model your team actually uses. |
| What validation is trusted | Validate after execute only helps when CI or validation signals are already meaningful. |
| Which paths are sensitive | Protected paths should be named before execute workflows are trusted on production repositories. |
This preparation is the difference between a controlled rollout and a noisy one.
Step 1: Open the Cloud Agents Workspace
Confirm plan access
If Cloud Agents is not available in your workspace, verify that the account is on Pro or above and that the feature is enabled for the workspace.
Review the top-level tabs
The workspace opens with tabs for Overview, Chat, Runs, Usage, Repositories, Approvals, Add-ons, and Settings.
Step 2: Connect GitHub and Verify Repository Access
Open Settings
Go to Settings inside Cloud Agents.
Check GitHub integration
In the settings overview, confirm that GitHub Integration shows a connected state and that the repositories you expect are listed.
Manage repository authorization if needed
If the repository is missing, use Manage Repositories and complete the GitHub authorization changes described in GitHub Integration.
Step 3: Add or Select a Repository
Open Repositories
Go to Repositories in the Cloud Agents workspace.
Add the repository
Use Add repository if the repository is not already configured.
Select the repository
In the Repository List panel, select the repository you want to automate.
Inspect defaults
Review the repository settings card group, especially Auto review, Auto execute, Review on PR events, and Validate after execute.
Step 4: Set Safety Before You Dispatch
Use conservative settings first.
| Control | Recommended first value | Why |
|---|---|---|
| Auto review | Enabled | Safe first pass for incoming change evaluation. |
| Auto execute | Disabled or limited | Prevents unattended write-style workflows while rules are still new. |
| Review on PR events | Enabled | Ensures PR activity produces timely analysis. |
| Validate after execute | Enabled | Adds a verification step before risky changes are considered complete. |
| Protected paths | Add critical directories | Keeps automation away from high-risk files until you trust the workflow. |
| Ignore paths | Add generated content | Reduces noisy reviews and false-positive changes. |
Do not enable broad execute automation on a production repository before you have defined protected paths and a human approval path.
See Repositories for the full repository policy model.
Choose a Rollout Style
Different teams should not start the same way.
| Style | Best for | Recommended setup |
|---|---|---|
| Observer mode | Teams new to the product or new to repo automation | Manual review runs only, execute disabled, protected paths defined early |
| Review-first mode | Most teams adopting Cloud Agents for the first time | Auto review on, PR signals on, execute manual, approvals active |
| Controlled execute mode | Teams that already trust the repo policy and want more throughput | Execute allowed in narrow scopes, validation on, approval checkpoints retained |
If you are unsure, choose Review-first mode. It gives the team value quickly without treating write-style automation as the starting point.
Step 5: Choose an Agent
Cloud Agents ships with system agents for core review and execute flows, and supports custom agents for team-specific behavior.
Start with a system agent
For the first pass, choose the built-in Code Review Agent for review runs and Execute Agent for code-change runs.
Use a custom agent only when the repository needs it
Add a custom agent once you know what should be specialized: migrations, docs, refactors, release checks, or another consistent operating pattern.
See Agents for agent design guidance.
Step 6: Launch Your First Review Run
Open Chat
Go to Chat.
Scope the run
Select the repository, branch, and agent in the top controls.
Choose the review path
Start a New Review run or select Code Review inside the new-run flow.
Write a precise task
Example:
Review the open pull request for auth callback changes. Focus on routing regressions, unsafe redirects, and missing tests. Do not suggest style-only edits.Submit and inspect
Track the run in Runs. Review the timeline, findings, and any approval requirement that appears.
Step 7: Launch Your First Execute Run
Start a new execute flow
From Chat or Overview, choose New Execute.
Select execute mode
In the new-run setup, choose Execute Change.
Keep scope narrow
Use repository and branch selectors, then provide a task with a clear goal and a small blast radius.
Example:
Add empty-state messaging to the approvals table in the dashboard. Limit changes to the approvals page and related tests.Review plan or direct execution mode
Use Plan first if the repository is new to Cloud Agents. Move to Agent mode once the operating pattern is stable.
Approve only after inspection
If the run pauses for approval, inspect the run detail page before approving or rejecting it.
A strong first rollout pattern is: enable repository review automation, keep execute runs manual, require approval on merge-capable outputs, and widen automation only after you have seen a few clean run cycles.
Step 8: Confirm the End-to-End Loop
After the first review and execute runs complete, verify the following:
- The repository appears under Repositories with the expected automation rules.
- The run history is visible under Runs.
- Any gated step appears under Approvals.
- Consumption appears under Usage.
What Success Looks Like After Week One
- Time to first review is materially lower than before.
- The approval queue is active but not overloaded.
- Most runs are Completed or intentionally Awaiting, not failing for avoidable setup reasons.
- Repository rules have already been refined from real run data instead of staying at their defaults.
If the First Week Goes Poorly
| Symptom | Usually means |
|---|---|
| Too many noisy findings | Prompts are too broad or ignore paths are incomplete |
| Too many approval pauses | Protected paths or execute scope need refinement |
| Too many failures | Branch scope, validation assumptions, or agent choice is wrong |
| Nobody trusts the output | The team started too aggressively; move back to review-first and tighten ownership |
A rough first week does not usually mean the product is a poor fit. It usually means the repository policy and rollout posture need tuning.
Next Steps
Workspace Tabs
Learn what each Cloud Agents tab is for before broadening adoption.
Chat & Dispatch
Understand Ask, Plan, and Agent modes plus the new-run workflow.
Repositories
Harden repository policy, protected paths, signals, and validation rules.
Runs
Inspect timelines, findings, artifacts, and approval checkpoints.
How is this guide?
Overview
Orchestrate parallel code review and code-change runs across GitHub repositories with scoped agents, approvals, safety rules, and full run visibility. Available on Pro and above.
Workspace Tabs
A tab-by-tab map of the Cloud Agents workspace, what each surface is for, and which operator questions each one answers.