trellis-meta

Guides customization of local Trellis workflow, hooks, agents, and platform files.

Updated Jun 8, 2026
One-click install
npx skills add https://github.com/dev2019zheng/codex-beacon --skill trellis-meta-dev2019zheng
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: trellis-meta
Source: https://github.com/dev2019zheng/codex-beacon/tree/main/.cursor/skills/trellis-meta
Command: npx skills add https://github.com/dev2019zheng/codex-beacon --skill trellis-meta-dev2019zheng

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? After running trellis init, AI assistants often lack a map of the generated .trellis/ directory and platform integration files, leading to edits in the wrong place (such as node_modules or upstream source) or broken workflow semantics. This Skill gives the AI a complete architectural model and customization entry points for local Trellis projects. ## Core Features & Use Cases - Architecture Reference: Explains the three-layer local Trellis model covering workflow.md, tasks, specs, workspace memory, and context injection. - Platform File Map: Documents where hooks, settings, agents, skills, and commands live across Claude Code, Cursor, Codex, Kiro, Gemini, and other platforms. - Customization Guides: Provides task-oriented guides for changing workflows, task lifecycles, context loading, hooks, agents, skills, and spec structure. - Use Case: A user asks to make the check agent run project-specific lint commands; the AI reads the change-agents guide, locates the platform's trellis-check agent file, and edits it while preserving role boundaries. ## Quick Start Ask the AI to use the trellis-meta skill to change the local Trellis workflow so that task creation is optional for small fixes.

Frequently Asked Questions about trellis-meta

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I customize the Trellis workflow in my project?▼

Edit .trellis/workflow.md, which is the local workflow source of truth defining phases, skill routing, and workflow-state prompt blocks. After editing, check that platform entry files like skills and commands still describe the same flow.

How do I change trellis-implement or trellis-check agent behavior?▼

Edit the platform agent files in your project, such as .claude/agents/trellis-*.md or .codex/agents/trellis-*.toml. Keep role boundaries intact, specify read order starting from the active task PRD, and define explicit write boundaries.

Which platforms does Trellis support for hooks and agents?▼

Trellis generates platform directories for Claude Code, Cursor, OpenCode, Codex, Kiro, Gemini CLI, Qoder, CodeBuddy, GitHub Copilot, Factory Droid, and Pi Agent. Main-session platforms like Kilo, Antigravity, and Windsurf rely on workflows and skills instead of sub-agents.

Why does my AI not see the current Trellis task in a new session?▼

Check whether the platform session-start hook is registered in settings and whether it calls .trellis/scripts/get_context.py. Also verify active task state exists in .trellis/.runtime/sessions/ and that the shell passes session identity.

Should I edit node_modules or Trellis source to customize behavior?▼

No. Default to editing generated local files inside your project: .trellis/ and platform directories. Only touch upstream Trellis source when you explicitly want to contribute a PR, fork the CLI, or change npm package contents.

Where should I put team-specific coding conventions in Trellis?▼

Put coding conventions in .trellis/spec/ under the appropriate layer with an index.md entry point, or create a project-local skill. Do not store team-private rules in the public trellis-meta skill, since updates could overwrite them.