# fengshao1227/ccg-workflow

多模型协作工作流引擎 — /ccg:go 一个命令，AI 自动分析意图、选择策略、编排 Codex + Gemini + Claude 协作执行

Repository: https://github.com/fengshao1227/ccg-workflow
Canonical: https://ross.abutalabs.com/products/ccg-workflow
Homepage: https://ccg.fengshao1227.com
Language: Go
License: MIT
License Family: permissive
Topics: claude-code, codex, gemini, workflow, agent-teams, ai, ccg, cli, llm, no-de, nodejs, prompt, opsxspec
Last push: 2026-08-26T08:11:13+00:00

## Health v2 (maintenance only)
Score: 69/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 60, longevity 17
- inputs: {"age_days": 241, "days_push": 7, "days_rel": 7, "gap_med": null, "n_releases_24m": 1}
- flags: prerelease_only
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5851, forks 445 (observed 2026-08-28T04:09:31.649983+00:00)

## What it is
CCG Workflow is a multi-model orchestration engine for Claude Code that coordinates Codex CLI, Gemini CLI, and Antigravity CLI from a single /ccg:go command. It analyzes task intent, selects an execution strategy, spawns parallel builder agents, and persists task state via hooks so progress survives context compaction or interruptions.

## Use cases
- orchestrate claude code with codex and gemini on one task
- run parallel ai agents on multi-file coding changes
- add jwt authentication to my api with ai workflow
- keep ai coding task state across context compaction
- cross-validate ai code changes with two models
- auto-run security and quality checks on ai-generated code

## When to choose
- you already use Claude Code and want multi-model collaboration
- large tasks benefit from parallel builder agents on separate files
- you need task state persisted across long or interrupted sessions
- you want automated quality gates on AI-generated changes

## When to avoid
- you don't use Claude Code as your primary coding assistant
- you prefer a single-model, minimal setup without extra CLI dependencies
- you need a fully offline workflow without API keys for multiple model providers

## Facets
- artifact type: cli-tool
- maturity: active
- function: agent-framework, workflow-automation, cli, prompt-engineering, mcp
- domain: large-language-models, developer-tools
- platform: cli, cross-platform
- tags: claude-code, codex-cli, gemini-cli, multi-model-orchestration, agent-teams, ai-coding-workflow, npm-installer, ai-agents, automation, command-line, nodejs

## Member repositories
- fengshao1227/ccg-workflow (main) score 69

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:31.649983+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:51:53.431799+00:00, confidence not recorded.
  - readme: https://github.com/fengshao1227/ccg-workflow (fetched 2026-08-28T04:09:31.649983+00:00, sha 7a67d3d50840)
  - homepage: https://ccg.fengshao1227.com (fetched 2026-08-29T08:47:15.269726+00:00, sha 8b8b0a63b673)
  - site_page: https://ccg.fengshao1227.com/getting-started (fetched 2026-08-29T08:47:15.278611+00:00, sha 61d7efd34967)
- Data as of 2026-08-30T08:39:29.467469+00:00.