auto-ralph-prep

auto-ralph-prep is a skill for Claude Code from dbinky/dbinky-skill-set. It costs 37 tokens per session (3,144 once invoked), scanned A, original, MIT.

A preparation tool that creates review files for Ralph, an automated refinement process, from a feature specification and related design or implementation documents.

In plain words
What is it for?
Use it before starting a Ralph review of a planned feature, when you have a specification and possibly design or implementation-plan documents.
Why use it?
It removes the need to answer setup questions manually and records what the review should examine, what gaps were found, and how the review should run.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions CLAUDE.md; mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the pr-review plugin — 8 skills, 15 agents shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add dbinky/dbinky-skill-set
Claude Code
/plugin install pr-review

Made for: Claude Code.

Or install pr-review, the plugin that ships this one along with the rest of its 8 skills, 15 agents.

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 auto-ralph-prep

README.md
[![agentmods](https://agentmods.dev/badge/skills/dbinky/dbinky-skill-set/auto-ralph-prep.svg)](https://agentmods.dev/skills/dbinky/dbinky-skill-set/auto-ralph-prep)
Your own site
<a href="https://agentmods.dev/skills/dbinky/dbinky-skill-set/auto-ralph-prep"><img src="https://agentmods.dev/badge/skills/dbinky/dbinky-skill-set/auto-ralph-prep.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,144 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00037 $0.03144
Opus 5 $0.00018 $0.01572
Sonnet 5 $0.00007 $0.00629
Haiku 4.5 $0.00004 $0.00314

Measured 5d ago against content hash cda3307b4ee2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

auto-ralph-prep 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 5d 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.

skills/auto-ralph-prep/SKILL.md · 248 lines

How it starts

The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auto Ralph Prep

You are generating ralph-o-matic review files without user interaction. This skill derives all configuration from the feature spec, design docs, implementation plans, and codebase scan — replacing the interactive Q&A in plan-to-ralph.

This is invoked either directly (/auto-ralph-prep) or via plan-to-ralph --auto.

Arguments

Parse the following from the user's command or calling skill:

  • SPEC_PATH (required): Path to the feature spec (e.g., docs/specs/user-auth-spec.md)
  • DESIGN_GLOB (optional): Glob for design docs (default: auto-derived from spec path by replacing -spec.md with -design-phase-*.md in the superpowers specs directory)
  • PLAN_GLOB (optional): Glob for implementation plans (default: auto-derived similarly)
  • --slug SLUG (optional): Feature slug for commit messages (default: derived from spec filename)

Prerequisites

Verify git repository:

git rev-parse --is-inside-work-tree

Verify spec file exists. If missing, stop with an error.

Phase 1: Archive

Check if any of these files exist:

  • RALPH.md
  • docs/reference/focus-areas.md
  • docs/reference/gaps-identified.md

If none exist: Skip to Phase 2.

If any exist: Archive them before regenerating, using the same pattern as plan-to-ralph:

  1. Create docs/reference/historical/ if it doesn't exist.
  2. Get today's date as YYYY-MM-DD.
  3. For each existing file, move (rename) it into docs/reference/historical/ as YYYY-MM-DD-historical-{filename}.md — do NOT copy it. The original must no longer exist at its working-tree location afterward.
  4. If a same-day backup already exists, append a counter: -2, -3, etc.

Why move instead of copy: Phase 5 regenerates each file fresh from the template embedded in this skill, which carries the required control semantics — notably the iteration/wrap-up protocol and the <promise> tag logic that lets the ralph server stop after repeated "no progress" iterations. Moving the originals out (rather than copying) guarantees they are absent when Phase 5 runs, so a previously mangled RALPH.md whose loop semantics were stripped can never survive into the new run. This subsumes the old legacy-format migration: any legacy or mangled RALPH.md is archived and replaced wholesale.

Read the full file on GitHub · 248 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. 5d ago First seen · 248 lines · 37 tokens per session scan A cda3307b4ee2

Subscribe to this mod's changes

auto-ralph-prep is a skill published in the GitHub repository dbinky/dbinky-skill-set (5 stars, last pushed 2mo ago), licensed MIT. It adds 37 tokens to every session and 3,144 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

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

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens