Skip to main content
A multi-agent pipeline where Claude Code orchestrates and Codex executes in parallel. CC analyzes the repo with GitNexus (knowledge graph) + ABCoder (AST), creates Trellis task PRDs with full architectural context, then Codex agents fill the coding spec files — each with access to the same code intelligence MCP tools.

​
Why This Skill?

AI coding agents produce better code when they have project-specific coding guidelines. But writing those guidelines manually is tedious. This skill automates the bootstrap:
  1. Claude Code analyzes your repo architecture using GitNexus + ABCoder
  2. Claude Code creates Trellis tasks with rich PRDs containing architectural context + MCP tool instructions
  3. Codex agents run those tasks in parallel, each filling one spec directory using the same MCP tools
The result: every spec file contains real code examples, actual patterns, and project-specific anti-patterns — not placeholder text.

​
Prerequisites

ToolPurposeRequired
TrellisWorkflow framework with .trellis/spec/ structureYes
GitNexusCode → knowledge graph (Tree-sitter + KuzuDB)Yes
ABCoderCode → UniAST (ts-morph for TS, tree-sitter for others)Yes
Codex CLIParallel task execution agentYes

​
Install

npx skills add mindfold-ai/Trellis/marketplace --skill cc-codex-spec-bootstrap
Or install all available skills: 
npx skills add mindfold-ai/Trellis/marketplace
Options:
FlagDescription
-gInstall globally (~/.claude/skills/)
-a claude-codeTarget a specific agent
-yNon-interactive mode

​
Verify Installation

Check if the skill is available: 
What skills do you have access to?
Claude should list cc-codex-spec-bootstrap in the response.

​
Usage

After installation, tell AI to bootstrap your specs: 
Bootstrap coding specs for this project using Codex

Set up Trellis spec files with code intelligence

Run the CC + Codex spec pipeline

​
How It Works

​
Phase 1 — Analyze

Claude Code indexes the repo with GitNexus (knowledge graph) and ABCoder (AST), then maps the architecture: package boundaries, module clusters, key patterns, and cross-package data flows.

​
Phase 2 — Plan

Claude Code creates one Trellis task per (package, layer) combination. Each task PRD contains the architectural context from Phase 1 plus MCP tool instructions so the Codex agent can independently explore the codebase.

​
Phase 3 — Execute

Codex agents run all tasks in parallel. Each agent reads its PRD, uses GitNexus + ABCoder MCP tools to analyze the relevant code, and fills the spec files with real examples and patterns.

​
What’s Included

FileContents
SKILL.mdFull pipeline instructions (3 phases, checklists, PRD templates)
references/mcp-setup.mdDetailed GitNexus + ABCoder MCP installation and configuration guide