What is Trellis
1.1 One-Line Summary
Trellis is scaffolding for AI coding assistants — it automatically injects your project specs into every AI session, so the AI writes code following your standards instead of improvising.
AI’s capabilities grow like vines — full of vitality but spreading everywhere.
Trellis is scaffolding for AI, guiding it along the path of your conventions.
1.2 Pain Points Addressed
| Pain Point | Current State | Trellis Solution |
|---|
| AI ignores your specs | You write CLAUDE.md, but AI forgets it after 5 conversation turns | Hook auto-injection ensures specs are included in every conversation |
| Fix A, break B cycle | AI fixes one bug but introduces another | Thinking Guides + Ralph Loop: think first, then act, then verify |
| Inconsistent code | AI-generated code runs but doesn’t integrate well | Cross-Layer Guide: map data flow before writing code |
| Scope creep | You ask for a button, AI writes 9,000 lines | Plan Agent: rejects and splits oversized requirements |
| Inconsistent team quality | Each person’s AI produces different coding styles | Shared Spec library — one person optimizes, the whole team benefits |
| Cross-session amnesia | New sessions require re-explaining project context | Session persistence — AI remembers context across sessions |
1.3 Comparison with Traditional Approaches
| Dimension | .cursorrules | CLAUDE.md | Skills | Trellis |
|---|
| Spec injection method | Manually loaded each conversation | Auto-loaded but easily truncated | User-initiated | Hook auto-injection, precisely loaded per task |
| Spec granularity | One large file | One large file | One per Skill | Modular files, composed per task |
| Cross-session memory | None | None | None | Workspace journal persistence |
| Parallel development | Not supported | Not supported | Not supported | Multi-Agent worktree parallelism |
| Quality control | None | None | None | Ralph Loop automatic verification |
| Team sharing | Single user | Single user | Shareable but no standard | Git-versioned Spec library |
| Platform support | Cursor only | Claude Code only | Per platform | Claude Code + Cursor + Codex + OpenCode + Kilo + Kiro |
1.4 Core Concepts at a Glance
| Concept | Description | Location |
|---|
| Spec | Your coding standards, written in Markdown. AI reads specs before writing code | .trellis/spec/ |
| Workspace | Each developer’s session logs, letting AI remember what was done last time | .trellis/workspace/ |
| Task | A work unit containing requirements docs and context configuration | .trellis/tasks/ |
| Hook | Auto-triggered scripts that inject context at session start, Agent invocations, etc. [Claude Code exclusive] | .claude/hooks/ |
| Agent | Specialized AI sub-processes such as Implement, Check, Debug, etc. [Claude Code exclusive] | .claude/agents/ |
| Skill | Reusable AI capability modules, shareable across projects | .claude/skills/ |
| Journal | Session log files recording what was done in each development session | .trellis/workspace/{name}/journal-N.md |
Hook and Agent systems are Claude Code exclusive features. Cursor, Codex, and other platforms load specs manually via Slash commands,
achieving the same effect. Spec, Workspace, Task, Journal, and other core concepts are universal across all platforms.
