Your First Task

3.1 Starting a Session

Claude Code
Cursor
Codex
OpenCode

Open the Claude Code terminal. The session-start.py Hook fires automatically and context is injected. You can describe your task directly, or run /start to see the full flow.The AI automatically performs the following:

Reads workflow.md to understand the development workflow
Runs get-context.py to get current state (your identity, Git status, active tasks)
Reads spec/frontend/index.md and spec/backend/index.md to understand project specs
Asks you: “What would you like to work on?”

Open Cursor. You must first enter:

/start

Only then will the AI load context. Cursor’s Hook support is still in development, so context loading currently requires manual command invocation.

Codex provides base context via AGENTS.md, but you need to run $start to get full project context (identity, Git status, active tasks, etc.).

OpenCode’s Hook system auto-injects context at session start, no need to manually run /start. Users can describe tasks immediately after opening the terminal. Optionally run /start for a more detailed context report.

3.2 AI Creates the Task and Develops

You say: “Add user login feature”. The AI will:

1. Invoke Research Agent to analyze the codebase
   → Find relevant spec files and code patterns

2. Create a task directory
   → .trellis/tasks/02-27-user-login/
   → Generate task.json, prd.md, implement.jsonl, etc.

3. Activate the task
   → task.py start (set .current-task)

4. Invoke Implement Agent
   → Hook auto-injects all specs configured in implement.jsonl
   → Agent implements the feature following specs

5. Invoke Check Agent
   → Hook injects check specs configured in check.jsonl
   → Agent checks code quality and auto-fixes issues
   → Ralph Loop ensures lint/typecheck passes

3.3 Testing and Committing

After the AI finishes, it will prompt you:

# Run project tests
pnpm lint && pnpm typecheck && pnpm test

# Commit after confirming everything works
git add src/components/LoginForm.tsx src/api/auth.ts
git commit -m "feat(auth): add user login feature"

3.4 Recording the Session

/record-session

The AI calls add-session.py to append the session content to your journal file and update your personal index.

3.5 Coming Back the Next Day — Cross-Session Memory

The next day, open a new session and enter /start:

AI: "Hi Alice! Yesterday you completed the user login feature (commit abc1234),
     including: LoginForm component, JWT middleware, users table.
     What would you like to work on today?"

The AI reads your workspace journal through the session-start.py Hook, remembering what you worked on last time.

Platform differences: Claude Code and OpenCode automatically read journals via Hooks for cross-session memory. Cursor and Codex users need to manually trigger context loading via /start (or $start) to get cross-session memory.

Quick Start Architecture Overview

OpenClaw

Trellis legacy · basics

Trellis legacy · advanced

Trellis legacy · customization

Trellis legacy · workflow

Trellis legacy · appendices

Skills and templates

Showcase and community

API reference

Agentic design patterns

Your First Task

Your First Task

3.1 Starting a Session

3.2 AI Creates the Task and Develops

3.3 Testing and Committing

3.4 Recording the Session

3.5 Coming Back the Next Day — Cross-Session Memory

​Your First Task

​3.1 Starting a Session

​3.2 AI Creates the Task and Develops

​3.3 Testing and Committing

​3.4 Recording the Session

​3.5 Coming Back the Next Day — Cross-Session Memory

Your First Task

3.1 Starting a Session

3.2 AI Creates the Task and Develops

3.3 Testing and Committing

3.4 Recording the Session

3.5 Coming Back the Next Day — Cross-Session Memory