# End-to-End Change Workflow

Runs a non-trivial change through analysis, design, build, review and test gates.

- Repository: https://github.com/fengshao1227/ccg-workflow (5956 stars)
- Category: Engineering
- License: MIT
- Last updated: 2026-10-21
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add fengshao1227/ccg-workflow --skill ccg-workflow -g -a claude-code -y`
Codex: `npx skills add fengshao1227/ccg-workflow --skill ccg-workflow -g -a codex -y`
Cursor: `npx skills add fengshao1227/ccg-workflow --skill ccg-workflow -g -a cursor -y`
Gemini CLI: `npx skills add fengshao1227/ccg-workflow --skill ccg-workflow -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add fengshao1227/ccg-workflow`

## Description

How to run a non-trivial change end to end with the CCG role tools (ccg_analyze / ccg_design / ccg_build / ccg_debug / ccg_optimize / ccg_review / ccg_test) and the verify-* quality gates. Use when a task is a whole feature, a refactor, a bug whose cause is not yet known, or any change large enough that one straight-through attempt would be a guess.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# CCG workflow

Seven role tools are available, each running a child agent on its own model with
its own expert persona. This is how to chain them so the work converges instead
of sprawling.

**Skip all of this for small, obvious work.** A one-line fix, a rename, a
question you can answer by reading two files, do it yourself. Delegation buys
depth, and it costs a round trip and a fresh context. Spend it only where depth
is the thing you lack.

## Picking a gear

Four modes. The user should not have to name one: read what they asked for,
pick, say which you picked in a line, and, for anything past Direct, say what
it costs and wait for a yes. They are paying per model call.

| Mode | For | Runs |
|------|-----|------|
| **Direct** | a one-line fix, a rename, a question you can answer by reading | you, alone |
| **Standard** | an ordinary feature, a bug with a known cause, a contained refactor | design → build → review |
| **Deep** | a design with real alternatives, an unclear bug, a migration, anything expensive to get wrong | analyze → design → build → test → review |
| **Team** | work that splits across files and will keep developing | `ccg_team`, several specialists at once, each owning its own files |

A role holding several models answers with all of them at once, so Deep costs
more than its phase count suggests, quote the real number of model calls, not
the number of phases. If the user names a mode, run that one. If a phase
changes what you believe, say so and re-pick rather than finishing a plan you
no longer believe in.

**Deep and Team are not a ranking.** Deep buys certainty about one thing by
asking several models about it. Team buys throughput on several things by
running colleagues at once. A hard question is Deep even if it is small; a wide
job is Team even if every part is easy. Something both hard and wide is Deep
first, settle the design and the contracts, then Team to build it.

## The loop

The rest: https://github.com/fengshao1227/ccg-workflow/blob/HEAD/dsh-ccg/skills/ccg-workflow/SKILL.md