Multi-Platform and Team Configuration

​

Multi-Platform and Team Configuration

​

Claude Code Full Experience

• Hook auto-injection — start working immediately upon opening terminal, no manual /start needed
• Multi-Agent Pipeline — /parallel orchestrates multiple worktree Agents in parallel
• Ralph Loop — automatic quality gate, Check Agent auto-retries on failure
• Agent system — 6 specialized Agents (dispatch, plan, implement, check, debug, research)

​

Cursor Integration

• Files located at .cursor/commands/trellis-{name}.md
• Cursor has 12 commands (no /parallel, as Cursor doesn’t support Multi-Agent Pipeline)
• No Hook support — spec injection requires manual command invocation
• No Agent system — all work happens in the main conversation
• No Ralph Loop — check commands must be run manually

# 1. Start session (required, replaces Hook auto-injection)
/trellis-start

# 2. Load relevant specs (recommended, replaces PreToolUse Hook)
/trellis-before-dev

# 3. Describe task, AI develops...

# 4. Manually check code quality (replaces Ralph Loop)
/trellis-check
/trellis-check-cross-layer     # Cross-layer check

# 5. Finish checklist
/trellis-finish-work

​

Codex Integration

trellis init --codex -u your-name

• AGENTS.md (root directory) — Codex entry file, provides base project context (similar to CLAUDE.md)
• .agents/skills/ — Shared Agent Skills directory (agentskills.io open standard, used by Codex, Kimi CLI, Amp, Cline, and others)
• .codex/config.toml — Project-scoped Codex configuration
• .codex/agents/ — Custom Codex agents (implement.toml, research.toml, check.toml)
• .codex/skills/ — Codex-specific skills (e.g. parallel for multi-agent pipelines)
• .codex/hooks/session-start.py + .codex/hooks.json — SessionStart hook that injects Trellis workflow, guidelines, and task context into Codex sessions

[features]
multi_agent = true
codex_hooks = true

​

Kilo Code Integration

trellis init --kilo -u your-name

project/
├── .kilocode/
│   └── workflows/                      # Commands (equivalent to slash commands)
│       ├── start.md                    # /start.md — session init
│       ├── brainstorm.md               # /brainstorm.md
│       ├── before-dev.md               # /before-dev.md
│       ├── check.md                    # /check.md
│       ├── check-cross-layer.md        # /check-cross-layer.md
│       ├── finish-work.md              # /finish-work.md
│       ├── break-loop.md               # /break-loop.md
│       ├── create-command.md           # /create-command.md
│       ├── integrate-skill.md          # /integrate-skill.md
│       ├── onboard.md                  # /onboard.md
│       ├── parallel.md                 # /parallel.md
│       ├── record-session.md           # /record-session.md
│       └── update-spec.md              # /update-spec.md

# 1. Run the start workflow for full context
/start.md

# 2. Switch to Orchestrator mode for complex tasks
# Kilo auto-decomposes tasks and assigns to Code/Architect modes

# 3. Describe task, AI develops...

# 4. Run check workflow
/check.md

# 5. Finish
/finish-work.md

​

Kiro Integration

trellis init --kiro -u your-name

project/
├── .kiro/
│   └── skills/                         # Agent Skills (YAML frontmatter + instructions)
│       ├── start/SKILL.md
│       ├── brainstorm/SKILL.md
│       ├── before-dev/SKILL.md
│       ├── check/SKILL.md
│       ├── check-cross-layer/SKILL.md
│       ├── finish-work/SKILL.md
│       ├── break-loop/SKILL.md
│       ├── create-command/SKILL.md
│       ├── integrate-skill/SKILL.md
│       ├── onboard/SKILL.md
│       ├── record-session/SKILL.md
│       └── update-spec/SKILL.md

# 1. Use the start skill to initialize session context
# 2. Describe task, AI develops...
# 3. Use the check skill to verify code quality
# 4. Use the finish-work skill for pre-commit checklist
# 5. Commit code when done

​

OpenCode Integration

trellis init --opencode -u your-name

• .opencode/commands/trellis/ — slash commands (start.md, before-dev.md, check.md, finish-work.md, and the rest of the 0.4 command set)
• .opencode/agents/ — sub-agent definitions (implement.md, research.md, check.md) for OpenCode’s Task-equivalent primitive
• .opencode/plugins/session-start.js — session-start plugin that injects Trellis context
• .agents/skills/ — shared Agent Skills layer (OpenCode also reads this directory)

​

iFlow Integration

trellis init --iflow -u your-name

• .iflow/commands/trellis/ — slash commands (/trellis:start, /trellis:before-dev, etc.)
• .iflow/hooks/session-start.py + .iflow/hooks.json — SessionStart hook wiring (same Python script as Claude Code)
• .iflow/settings.json — project-scoped iFlow config

​

Gemini CLI Integration

trellis init --gemini -u your-name

• .gemini/commands/trellis/{name}.toml — TOML command files for the 0.4 command set. Gemini CLI loads them via its TOML command format, so each command’s prompt lives in a prompt = """...""" block.
• .agents/skills/ — shared skills layer (Gemini CLI reads the agentskills.io standard path).

​

Qoder Integration

trellis init --qoder -u your-name

• .qoder/skills/{name}/SKILL.md — the full 0.4 command set rendered as skills (start, brainstorm, before-dev, check, check-cross-layer, finish-work, break-loop, create-command, integrate-skill, onboard, record-session, update-spec). The platform auto-matches based on user intent.

​

GitHub Copilot Integration

trellis init --copilot -u your-name

• .github/copilot-instructions.md — auto-loaded every chat session, carries the Trellis prelude
• .github/prompts/trellis-{name}.prompt.md — per-command prompts (trellis-start.prompt.md, trellis-check.prompt.md, etc.). Invoke via Copilot’s “Run Prompt” picker.

​

Windsurf Integration

trellis init --windsurf -u your-name

• .windsurf/workflows/trellis-{name}.md — each Trellis command as a workflow, invoked from Windsurf’s workflow picker
• .windsurf/rules/trellis.md — always-on rule carrying the Trellis prelude

​

CodeBuddy Integration

trellis init --codebuddy -u your-name

• .codebuddy/commands/trellis/{name}.md — 12 slash commands (invoked as /trellis:start, /trellis:check, etc.)

​

Antigravity Integration

trellis init --antigravity -u your-name

• .agent/workflows/{name}.md — Trellis workflows, invoked via Antigravity’s workflow picker. Content is adapted from the shared Codex skill source.

​

Factory Droid Integration

trellis init --droid -u your-name

• .factory/commands/trellis/{name}.md — slash commands
• .factory/agents/{name}.md — sub-agent definitions (implement, research, check)
• .factory/skills/ — auto-trigger skills
• .factory/hooks/session-start.py + .factory/hooks.json — SessionStart hook (same Python script family as Claude Code)

​

Operating System Compatibility

​

Multi-Developer Collaboration

• workspace/{name}/ — each developer has their own directory
• .developer — gitignored, per-developer
• Parallel task worktrees — physically isolated

• spec/ — multiple people may modify the same spec simultaneously
• tasks/ — multiple people may operate on the same task

• Spec changes go through PR review
• Task assignments are explicit (--assignee parameter)
• Important spec changes are discussed in team meetings

​

Complete worktree.yaml Configuration

# Worktree Configuration for Multi-Agent Pipeline

#───────────────────────────────────────────────────
# Paths
#───────────────────────────────────────────────────

# Worktree storage directory (relative to project root)
worktree_dir: ../trellis-worktrees

#───────────────────────────────────────────────────
# Files to Copy
#───────────────────────────────────────────────────

# Files that need independent copies in each worktree
# These files contain sensitive info or need independent config
copy:
  - .env                     # Environment variables
  - .env.local               # Local environment variables
  - .trellis/.developer      # Developer identity

#───────────────────────────────────────────────────
# Post-Create Hooks
#───────────────────────────────────────────────────

# Commands to run after creating a worktree
# Executed sequentially in the worktree directory; aborts on failure
post_create:
  - pnpm install --frozen-lockfile
  # - npm install
  # - yarn install --frozen-lockfile

#───────────────────────────────────────────────────
# Check Agent Verification (Ralph Loop)
#───────────────────────────────────────────────────

# Commands to verify code quality
# When configured, Ralph Loop runs these — all must pass
# Without configuration, falls back to completion markers mode
verify:
  - pnpm lint
  - pnpm typecheck
  # - pnpm test

​

trellis update and Version Management

# Check current version
cat .trellis/.version

# Update to latest version
trellis update

# Preview updates (dry run)
trellis update --dry-run

# Force overwrite all files
trellis update -f

# Skip all changed files
trellis update -s

1. Compute local file hashes
2. Compare with recorded template hashes
3. If they match — file not modified by user — safe to update
4. If they differ — file was modified by user — prompt for conflict resolution
5. User chooses: overwrite / skip / merge