CCG is a command-line workflow engine that coordinates Claude, Codex, Gemini, and other models as specialized collaborators on coding tasks. It is used to analyze requests, choose a strategy, delegate work to model-specific roles, and combine their results. The catalogue entries provide the skills, commands, agents, and plugin that implement this workflow.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/fengshao1227/ccg-workflowWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/fengshao1227/ccg-workflow/clean-branches)<a href="https://agentmods.dev/commands/fengshao1227/ccg-workflow/clean-branches"><img src="https://agentmods.dev/badge/commands/fengshao1227/ccg-workflow/clean-branches.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00023 | $0.00751 |
| Opus 5 | $0.00012 | $0.00376 |
| Sonnet 5 | $0.00005 | $0.00150 |
| Haiku 4.5 | $0.00002 | $0.00075 |
Grade A, and why
clean-branches scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- clean-branches — 100% identical, 0 lines differ
What it actually says
Clean-Branches - 清理 Git 分支
安全识别并清理已合并或长期未更新的分支。
使用方法
/clean-branches [options]
选项
| 选项 | 说明 |
|---|---|
--base <branch> |
基准分支（默认 main/master） |
--stale <days> |
清理超过 N 天未更新的分支 |
--remote |
同时清理远程分支 |
--dry-run |
只预览，不执行（默认） |
--yes |
跳过确认直接删除 |
--force |
强制删除未合并分支 |
执行工作流
🔍 阶段 1：预检
[模式：准备]
- 同步远端：
git fetch --all --prune - 读取保护分支配置
- 确定基准分支
📋 阶段 2：分析识别
[模式：分析]
已合并分支：
- 已完全合并到
--base的分支
过期分支（如指定 --stale）：
- 最后提交在 N 天前的分支
排除：
- 从待清理列表中移除保护分支
📊 阶段 3：报告预览
[模式：报告]
## 将要删除的分支
### 已合并分支
- feature/old-feature (合并于 3 天前)
- bugfix/fixed-issue (合并于 7 天前)
### 过期分支
- experiment/old-test (最后更新 90 天前)
✅ 阶段 4：执行清理
[模式：执行]
仅在不带 --dry-run 且确认后执行：
# 本地分支
git branch -d <branch>
# 远程分支（如果 --remote）
git push origin --delete <branch>
# 强制删除（如果 --force）
git branch -D <branch>
保护分支配置
# 添加保护分支
git config --add branch.cleanup.protected develop
git config --add branch.cleanup.protected 'release/*'
# 查看保护分支
git config --get-all branch.cleanup.protected
示例
# 预览将清理的分支
/clean-branches --dry-run
# 清理已合并且超过 90 天未动的分支
/clean-branches --stale 90
# 清理已合并到 release/v2.1 的分支
/clean-branches --base release/v2.1 --remote --yes
最佳实践
- 优先 dry-run – 先预览再执行
- 活用 --base – 适配 release 工作流
- 谨慎 --force – 除非确定无用
- 团队协作 – 清理远程分支前先通知
- 定期运行 – 每月/季度一次保持清爽
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 118 lines · 23 tokens per session scan A 76fcb096a184
clean-branches is a command published in the GitHub repository fengshao1227/ccg-workflow (5,879 stars, last pushed 5d ago), licensed MIT. It adds 23 tokens to every session and 751 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
resolve-pr
Resolve PR review feedback — fetch unresolved threads, triage, dispatch resolver agents, reply + resolve via GraphQL.
ship
Ship: review gate, tests, version bump, changelog, conventional commit, docs update, PR. Complete pipeline from done to merged.
analyze-git
Perform a comprehensive analysis of the git repository to identify branches and worktrees that can be cleaned up. This is a READ-ONLY analysis - no deletions will be performed.
maestro-fork
Create or sync session worktree for parallel dev.
release
A command that carries out a release workflow for the nanobanana-adc project, including version checks, changelog updates, tests, builds, and release preparation.
release-swarm
Orchestrate complex software releases using AI swarms that handle everything from changelog generation to multi-platform deployment.