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/samqin123/Claude_skill_poolWrote 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/samqin123/claude_skill_pool/ralph-yolo)<a href="https://agentmods.dev/commands/samqin123/claude_skill_pool/ralph-yolo"><img src="https://agentmods.dev/badge/commands/samqin123/claude_skill_pool/ralph-yolo/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/samqin123/claude_skill_pool/ralph-yolo"><img src="https://agentmods.dev/badge/commands/samqin123/claude_skill_pool/ralph-yolo.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00018 | $0.02603 |
| Opus 5.5 | $0.00007 | $0.01041 |
| Sonnet 5.5 | $0.00004 | $0.00521 |
| Haiku 4.5 | $0.00002 | $0.00260 |
Grade A, and why
ralph-yolo 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ralph YOLO - 自主 Agent 循环(无 Amp 依赖)
Ralph YOLO 是 Ralph 的轻量版本,直接使用 Claude Code 的 Task tool 管理子 agent 完成任务,无需 Amp CLI。
使用方法
/ralph-yolo [path-to-prd.md]
示例:
/ralph-yolo tasks/prd-my-feature.md # 从 PRD 转换并执行
/ralph-yolo prd.json # 使用现有 prd.json 执行
/ralph-yolo # 自动查找 prd.json
Phase 1: PRD 转换(如果提供 markdown PRD)
Step 1: 检查输入
检查用户是否提供了 PRD 文件路径。如果没有,查找项目根目录的 prd.json。
用户输入格式:
/ralph-yolo tasks/prd-my-feature.md- 转换 PRD 并运行 Ralph YOLO/ralph-yolo prd.json- 使用现有 prd.json 运行/ralph-yolo- 运行(查找 prd.json)
Step 2: 归档旧运行(如需要)
检查是否存在 prd.json 且 branchName 不同。如果是:
- 读取当前
prd.json提取branchName - 比较新功能的分支名
- 如果不同且
prd-progress.txt有内容:- 创建归档文件夹:
.claude/archive/YYYY-MM-DD-[feature-name]/ - 复制当前
prd.json和prd-progress.txt到归档 - 重置
prd-progress.txt为新的头部信息
- 创建归档文件夹:
Step 3: 转换为 prd.json
解析 PRD 并生成项目根目录的 prd.json:
{
"project": "[从 PRD 提取或自动检测的项目名]",
"branchName": "ralph/[feature-name-kebab-case]",
"description": "[从 PRD 提取的功能描述]",
"userStories": [
{
"id": "US-001",
"title": "[故事标题]",
"description": "As a [用户], I want [功能] so that [收益]",
"acceptanceCriteria": [
"标准 1",
"标准 2",
"Typecheck passes"
],
"priority": 1,
"passes": false,
"notes": ""
}
]
}
转换规则
- 每个用户故事成为一个 JSON 条目
- ID:顺序编号(US-001, US-002 等)
- Priority:基于依赖顺序(schema → backend → UI)
- 所有故事:初始
passes: false,notes为空 - branchName:从功能名派生,kebab-case,前缀
ralph/ - 始终添加:"Typecheck passes" 到每个故事
- UI 故事:添加 "Verify in browser"
故事大小关键原则
每个故事必须在一个上下文窗口内完成。
合适大小:
- 添加数据库列和迁移
- 向现有页面添加 UI 组件
- 更新服务器操作
- 添加过滤下拉菜单
太大(需拆分):
- "构建整个仪表板" → 拆分为:schema, queries, UI 组件, filters
- "添加认证" → 拆分为:schema, middleware, 登录 UI, session handling
经验法则: 如果不能用 2-3 句话描述变更,就太大了。
故事排序
故事按 priority 顺序执行。前面的故事不能依赖后面的。
正确顺序:
- Schema/数据库变更(migrations)
- Server actions / 后端逻辑
- 使用后端的 UI 组件
- 汇总数据的 Dashboard/summary 视图
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.
- 2mo ago First seen · 347 lines · 18 tokens per session scan A 2754e6b4c2b8
ralph-yolo is a command published in the GitHub repository samqin123/Claude_skill_pool (2 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 18 tokens to every session and 2,603 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.
ralph-yolo compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ralph-yolosamqin123/Claude_skill_pool | Command | 2 | 8mo ago | Apache-2.0 | A | 18 | Claude Code |
| checklistgithub/spec-kit | Command | 148k | today | MIT | A | 13 | Claude Code |
| clarifygithub/spec-kit | Command | 148k | today | MIT | A | 27 | Claude Code |
| specifygithub/spec-kit | Command | 148k | today | MIT | A | 13 | Claude Code |
| analyzegithub/spec-kit | Command | 148k | today | MIT | A | 26 | Claude Code |
| convergegithub/spec-kit | Command | 148k | today | MIT | A | 35 | Claude Code |
| implementgithub/spec-kit | Command | 148k | today | MIT | A | 14 | Claude Code |