ralph-yolo

ralph-yolo is a skill for Gemini CLI from samqin123/Claude_skill_pool. It costs 40 tokens per session (4,172 once invoked), scanned A, original, Apache-2.0.

A workflow that uses Claude Code sub-agents to carry out a product requirements document, or PRD, one user story at a time. A PRD is a document describing what a product or feature should do.

In plain words
What is it for?
Use it with a Markdown PRD or prd.json file to create or update the plan, archive an older run when needed, and execute each user story in order through sub-agents.
Why use it?
It turns a written feature plan into tracked implementation work without requiring the separate Amp command-line tool, while keeping the main session informed of progress.

Skill for Gemini CLI

Written for Gemini CLI: installed under .gemini/. Also seen: mentions Claude Code.

Good fit Use it with a Markdown PRD or prd.json file to create or update the plan, archive an older run when needed, and execute each user story in order through sub-agents.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/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.

Any agent
npx skills add samqin123/Claude_skill_pool --skill ralph-yolo
Clone the repo
git clone --depth 1 https://github.com/samqin123/Claude_skill_pool

Made for: Gemini CLI.

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/skills/samqin123/claude_skill_pool/ralph-yolo/github.svg)](https://agentmods.dev/skills/samqin123/claude_skill_pool/ralph-yolo)
Your own site
<a href="https://agentmods.dev/skills/samqin123/claude_skill_pool/ralph-yolo"><img src="https://agentmods.dev/badge/skills/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.

agentmods 80×15 button for ralph-yolo

Your own site · 80×15
<a href="https://agentmods.dev/skills/samqin123/claude_skill_pool/ralph-yolo"><img src="https://agentmods.dev/badge/skills/samqin123/claude_skill_pool/ralph-yolo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,172 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 $0.00040 $0.04172
Opus 5 $0.00020 $0.02086
Sonnet 5 $0.00008 $0.00834
Haiku 4.5 $0.00004 $0.00417

Measured 9d ago against content hash e964861a2ac5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 9d 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/.gemini/skills/ralph-yolo/SKILL.md · 614 lines

How it starts

The opening of the file, as written. The whole thing — 614 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ralph YOLO - Autonomous Agent Loop (No Amp Required)

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,无需依赖 Amp CLI。


与原 Ralph 的区别

特性 原 Ralph Ralph YOLO
依赖 Amp CLI Claude Code Task Tool
执行方式 bash 脚本循环 前台子 agent 管理
Agent 实例 外部 Amp 进程 Claude Code Task 子 agent
状态跟踪 文件读写 前台实时更新
上下文 每次全新 主会话保持完整上下文

使用方法

/ralph-yolo [path-to-prd.md]

如果未提供 PRD 路径,会查找项目根目录的 prd.json 并直接执行。

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

工作流程

Phase 1: PRD 转换(如果提供了 markdown PRD)

Step 1: 读取 PRD 文件

读取用户提供的 markdown PRD 文件。

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

Read the full file on GitHub · 614 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. 9d ago First seen · 614 lines · 40 tokens per session scan A e964861a2ac5

Subscribe to this mod's changes

ralph-yolo is a skill published in the GitHub repository samqin123/Claude_skill_pool (2 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 40 tokens to every session and 4,172 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens