Guides

Each guide solves one problem end to end, with a complete config you can deploy and the output it produces. If you are new, start with the Quickstart and Your first agent.

Automate a recurring chore

• How to automate your daily standup. A cron agent reads yesterday's merged pull requests and writes the summary itself, on a read-only token.
• How to keep your skills from going stale. A daily agent compares the day's merges against what your skills claim, and opens a pull request when the code has moved past them.

Work on pull requests

• How to review every pull request as commits land. A reviewer that reads each push as it arrives and never re-comments a line it already reviewed.
• How to keep pull request descriptions up to date. Rewrite the description on every push so reviewers read what the branch does now, preserving anything the author wrote by hand.
• How to review database migrations before they merge. A specialist reviewer scoped by paths, checking locking, backfills, and rollout order.
• How to add screenshots to every pull request. Agents upload images that outlive the sandbox and paste org-gated links, so a UI change arrives with proof it renders.

Answer questions and respond to alerts

• How to answer codebase questions from GitHub, Slack, and Linear. Mention @ellipsis where the question was asked and get an answer from an agent with the code in front of it.
• How to build a custom Slackbot with access to your code. A Slack-only mention agent that answers from your codebase, opens pull requests, and runs your internal tools.
• How to turn Sentry alerts into root-cause diagnoses. React to alerts with an agent that reads the stack trace, finds the code path, and posts a diagnosis or opens a fix.

Set up the environment

• How to give agents the tools and credentials your build needs. Bake your toolchain into a cached image, run setup hooks, and inject credentials so agents can build and test your code.
• How to teach every agent your team's conventions. Write your conventions once as a skill and have every agent load it when the task calls for it.
• How to bill agent tokens to your own Anthropic account. Route model calls through your own Anthropic API key, with your rate limits and commitments.

Drive agents yourself

• How to trigger agents from your own scripts and CI. Start, watch, and stop sessions over HTTP from a CI job or your own service.
• How to search every agent session your team has run. Pull laptop Claude Code sessions into the same searchable history as your cloud agents.