ralph-yolo

ralph-yolo is a command for Claude Code from samqin123/Claude_skill_pool. It costs 18 tokens per session (2,603 once invoked), scanned A, original, Apache-2.0.

An autonomous coding command that turns a product requirements document (PRD) into a task list and runs coding sub-agents to complete it.

In plain words
What is it for?
Use it to run `/ralph-yolo` with a Markdown PRD, an existing `prd.json` task file, or no file when `prd.json` is already in the project.
Why use it?
It removes the need to break a feature request into tasks and manage each coding step manually. It can also archive progress from an older run when starting a different feature.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Claude Code.

Good fit Use it to run /ralph-yolo with a Markdown PRD, an existing prd.json task file, or no file when prd.json is already in the project.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/samqin123/claude_skill_pool/ralph-yolo
Install

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.

Clone the repo
git clone --depth 1 https://github.com/samqin123/Claude_skill_pool

Made for: Claude Code.

Wrote 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.

agentmods badge for ralph-yolo

README.md
[![agentmods](https://agentmods.dev/badge/commands/samqin123/claude_skill_pool/ralph-yolo.svg)](https://agentmods.dev/commands/samqin123/claude_skill_pool/ralph-yolo)
Your own site
<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="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,603 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00018 $0.02603
Opus 5 $0.00009 $0.01301
Sonnet 5 $0.00004 $0.00521
Haiku 4.5 $0.00002 $0.00260

Measured 8d ago against content hash 2754e6b4c2b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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 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.

package/full-dev-脚手架/.claude/commands/ralph-yolo.md · 347 lines

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.jsonbranchName 不同。如果是:

  1. 读取当前 prd.json 提取 branchName
  2. 比较新功能的分支名
  3. 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.jsonprd-progress.txt 到归档
    • 重置 prd-progress.txt 为新的头部信息

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

  1. 每个用户故事成为一个 JSON 条目
  2. ID:顺序编号(US-001, US-002 等)
  3. Priority:基于依赖顺序(schema → backend → UI)
  4. 所有故事:初始 passes: falsenotes 为空
  5. branchName:从功能名派生,kebab-case,前缀 ralph/
  6. 始终添加:"Typecheck passes" 到每个故事
  7. 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:

  1. Schema/数据库变更(migrations)
  2. Server actions / 后端逻辑
  3. 使用后端的 UI 组件
  4. 汇总数据的 Dashboard/summary 视图

Read the full file on GitHub · 347 lines

Changes

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.

  1. 8d ago First seen · 347 lines · 18 tokens per session scan A 2754e6b4c2b8

Subscribe to this mod's changes

ralph-yolo is a command published in the GitHub repository samqin123/Claude_skill_pool (2 stars, last pushed 6mo 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. 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.