Building Agents with Claude Code

Choose a wizard and run it

/create-agent:create        # Shows all available wizards

# Or jump directly to a specific wizard:
/create-agent:prospector    # B2B sales research agent
/create-agent:chief-of-staff # Executive assistant
/create-agent:webmaster     # Website management
/create-agent:recon         # Competitive intelligence
/create-agent:ghostwriter   # Content writer
/create-agent:custom        # Blank canvas (you define everything)

Each wizard asks domain-specific questions and scaffolds a complete agent.

Connect to Trinity (one-time)

/trinity:connect

Authenticates and saves your MCP connection config. Only needed once per machine.

Add your GitHub token (one-time)

Deployment is repository-first — Trinity clones the agent from its GitHub repo and tracks the branch. In the Trinity UI, go to Settings → GitHub token and add a fine-grained PAT with Contents: Read on the repos your agents live in. Public repos work without one.

Push, then deploy to Trinity

git push                # the wizard already initialized and committed the repo
/trinity:onboard

Checks compatibility, fills in anything missing in template.yaml (declared credentials, schedules, plugins), verifies the repo is pushed and readable, and deploys from it. Your agent is now running 24/7 — turn on its autonomy toggle in the UI when you want its schedules to start firing.

Connect to Trinity (one-time)

/trinity:connect

Onboard the agent

/trinity:onboard

Checks your agent for Trinity compatibility, creates required files (template.yaml, .env.example, .mcp.json.template, .gitignore), and deploys — from the agent's GitHub repo by default, from local files as the fallback when there is no repo yet.

Already deployed it from a bare repo? If you created the agent in Trinity straight from a repository that had no template.yaml — someone else's agent, or one you didn't want to adapt locally — run /trinity:onboard inside that agent — send it /trinity:onboard in-place as a chat message, or run it from the agent's terminal — and it takes the Onboard in place path. It writes the Trinity files, installs and declares the plugins, pushes the result back to the repo, reconciles schedules, and verifies with the platform's compatibility report. See Onboarding a deployed agent in place.

Review and improve (optional)

/create-agent:review    # Read-only audit — prioritized findings, no changes
/create-agent:adjust    # Apply the improvements

review audits your agent against best practices without changing anything; adjust proposes and applies improvements to CLAUDE.md, skills, and Trinity files.

Add a new skill/playbook

/agent-dev:create-playbook

Add a memory system

/agent-dev:add-memory   # Choose: file-index, brain, json-state, workspace

Add GitHub Issues task management

/agent-dev:add-backlog

Push changes to Trinity

git push
/trinity:sync          # advances the deployed agent; also reconciles schedules + plugins