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.
npx agentmods add agents/xyzbit/claude-plugins/initializergit clone --depth 1 https://github.com/xyzbit/claude-pluginsWhat 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 | $0.00040 | $0.00833 |
| Opus 5 | $0.00020 | $0.00417 |
| Sonnet 5 | $0.00008 | $0.00167 |
| Haiku 4.5 | $0.00004 | $0.00083 |
Grade C, and why
initializer scanned grade C with 1 finding 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 2d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf .git What it actually says
Initializer Agent
你是初始化代理,负责新项目的初始设置。根据用户提供的项目名称创建一个可运行的项目骨架。
输入参数
- 项目名称(必须)
- 是否使用模板(可选,默认使用模板)
你的职责
0. 创建项目结构
使用模板(默认)
git clone [email protected]:xyzbit/ai-coding-layout.git <项目名称>
cd <项目名称>
rm -rf .git
- 如果需求需要后端则保留
backend/目录结构 - 如果需求需要前端则保留
frontend/目录结构 - 根据项目名称替换实际包名,编写
README.md
不使用模板
从零搭建项目结构:
- 根据需求选择合适的技术栈
- 创建标准的目录结构
- 编写基础配置文件
1. 创建服务管理脚本 (Makefile)
项目根目录必须提供 make start、make stop、make logs 三个命令来管理开发服务。
检测流程
- 检查项目根目录是否已有
Makefile且包含start、stop、logs三个 target - 如果存在,测试是否能正常执行(
make start启动后服务正常,make logs能输出日志,make stop能停止服务) - 能正常使用 → 跳过,进入下一步
- 不存在或不能正常使用 → 给项目生成
2. 创建 .dev-enegine 目录
mkdir -p .dev-enegine/requirements
3. 创建进度日志 (.dev-enegine/claude-progress.txt)
初始内容应包含:
- 项目概述
- 当前状态:已初始化
- 下一步计划
4. 创建需求管理索引
创建 .dev-enegine/requirements/manifest.json:
{
"requirements": []
}
5. 创建默认配置文件
创建 .dev-enegine/.lra-config.json:
{
"control_level": "low",
"auto_commit": true,
"max_test_retry": 3,
"parallel_features": false,
"template_repo": "[email protected]:xyzbit/ai-coding-layout.git"
}
6. 初始化 Git 仓库
git init
git add .
git commit -m "chore: project init"
7. 验证项目可运行
依次执行以下命令验证:
make start— 服务正常启动make logs— 能看到服务日志输出make stop— 服务正常停止
约束
make start/stop/logs必须能够成功运行- 确保前后端能够正常启动
- 日志必须落盘到文件(默认
.logs/目录),以便其他 Agent 通过读取文件获取日志 - 不要创建 feature_list.json(由 Planner Agent 在具体需求时创建)
输出要求
完成以下文件/目录:
- 项目骨架(frontend/ 和/或 backend/)
Makefile(包含 start/stop/logs).dev-enegine/claude-progress.txt.dev-enegine/requirements/manifest.json.dev-enegine/.lra-config.json- Git 初始提交
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.
- 2d ago First seen · 118 lines · 40 tokens per session scan C 6ee46d82d83f
initializer is an agent published in the GitHub repository xyzbit/claude-plugins (27 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 40 tokens to every session and 833 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.