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 skills/magic3007/dotfiles/ralph-loopnpx skills add magic3007/dotfiles --skill ralph-loopgit clone --depth 1 https://github.com/magic3007/dotfilesWrote 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/skills/magic3007/dotfiles/ralph-loop)<a href="https://agentmods.dev/skills/magic3007/dotfiles/ralph-loop"><img src="https://agentmods.dev/badge/skills/magic3007/dotfiles/ralph-loop.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 | $0.00063 | $0.03443 |
| Opus 5 | $0.00032 | $0.01722 |
| Sonnet 5 | $0.00013 | $0.00689 |
| Haiku 4.5 | $0.00006 | $0.00344 |
Grade A, and why
ralph-loop 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 yesterday.
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 — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex compatibility
When this skill uses Claude Code terminology, apply these mappings:
- Resolve bundled files relative to
${CODEX_HOME:-$HOME/.codex}/skills/ralph-loop. - Use
request_user_inputwhen it is available; otherwise ask the user directly instead of callingAskUserQuestion. - Use
update_planfor task lists, shell execution forBash,rgforGlob/Grep, and Codex file inspection/editing tools forRead/Write/Edit. - Treat
$ARGUMENTSas the user's request arguments. Commands prefixed with!are instructions to run explicitly; Codex does not evaluate them on load. - Use
AGENTS.mdand.codex/for Codex project guidance. Only operate onAGENTS.mdor.claude/when the task explicitly targets Claude Code. - Named
mcp__...tools require the matching installed MCP server or app. If it is unavailable, report the dependency and use a documented safe fallback only when this skill provides one.
Ralph Loop v2 (Claude Code Edition)
基于 Geoffrey Huntley 的 Ralph Wiggum 技术的自主迭代开发。
核心： 每个阶段有强制 code review + 测试 gate，不通过不进下一阶段。
触发短语
| 短语 | 动作 |
|---|---|
| "Ralph loop over X" | 问走哪个阶段 |
| "Interview me about X" | Phase 1: 需求收集 |
| "Plan system X" | Phase 2: 规划循环 |
| "Build system X" | Phase 3: 构建循环 |
核心原则
- Context 是稀缺的 — 每次迭代做合理的一块工作，不贪多也不过少
- 你只是任务中的一环 — loop.sh 驱动迭代，每次 CLI 调用是独立的 context，做完合理粒度就退出
- 计划是一次性的 — 跑偏了重新规划，不硬撑
- 背压 > 方向 — 测试 + review 自动拒绝错误输出
- 每阶段有 gate — code review + 测试通过才能推进
三阶段工作流
Phase 1: REQUIREMENTS ──── 人机对话 → specs/*.md
Gate: 用户确认所有 spec
Phase 2: PLANNING ──────── 差距分析 → IMPLEMENTATION_PLAN.md
Gate: Plan review + 验证（命令存在、路径有效）
Phase 3: BUILDING ──────── 迭代实现 → test → Codex review → commit
Gate: 测试通过 + Codex cross-review（完成时）
阶段检测
| 当前状态 | 阶段 | 动作 |
|---|---|---|
没有 specs/ 或为空 |
Phase 1 | 跑需求访谈 |
有 specs/*.md，没有 IMPLEMENTATION_PLAN.md |
Phase 2 | 跑规划循环 |
| 有 spec + plan | Phase 3 | 跑构建循环 |
| Plan 显示全部完成 | Done | 汇报 |
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 348 lines · 63 tokens per session scan A e8672b69403f
ralph-loop is a skill published in the GitHub repository magic3007/dotfiles (11 stars, last pushed yesterday), licensed MIT. It adds 63 tokens to every session and 3,443 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
assess-quality
Foundational quality framework: the five questions (readable, easy to start, expands without bloat, consistent, intentional) every other dev skill is judged against, plus the dual-audience and workshop principles. Use when onboarding to a project, defining a quality bar, setting an assessment checklist, or arbitrating…
create-oss-skill
Create well-formed Agent Skills following the agentskills.io specification. Scaffold directories, write SKILL.md files, bundle scripts, and structure instructions for progressive disclosure. Use when creating a new skill, reviewing skill structure, optimizing a skill description, or setting up evals for skill quality.
orchestrate-agents
Orchestrate multiple agent CLIs (Claude, Codex, Antigravity) via tmux with a shared fleet store, dispatching one guardian subagent per pane. Survey-first: inspects and adopts existing tmux sessions, windows, and agent panes before creating anything new. Use when running a multi-agent session, dispatching parallel…
extend-oss-skills-to-claude
Extend standard agentskills.io skills with Claude Code-specific features. Invocation control, subagent execution, dynamic context injection, string substitutions, model/effort overrides, and deployment scoping. Use when adapting a portable skill for Claude Code, adding Claude-specific frontmatter, setting up subagent…
merge-ready
Drive an existing pull request to a mergeable state: get CI green, resolve merge conflicts with the base branch, address and resolve review comments, trigger required bot reviews/approvals (e.g. commenting '@claude review'), link associated issues, and clean up the PR title and description. Ends with a readiness…
scaffold-project
Generates cross-language standard files (README, AGENTS.md, LICENSE, CONTRIBUTING.md, SECURITY.md, sr.yaml, .envrc, llms.txt), documentation conventions, and project structure, then dispatches to language-specific scaffolds. Use first for cross-language standard files and structure, THEN load the matching scaffold…