Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/RobinOppenstam/claude-ralphnpx agentmods add skills/robinoppenstam/claude-ralph/ralphWrote 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/robinoppenstam/claude-ralph/ralph)<a href="https://agentmods.dev/skills/robinoppenstam/claude-ralph/ralph"><img src="https://agentmods.dev/badge/skills/robinoppenstam/claude-ralph/ralph/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/skills/robinoppenstam/claude-ralph/ralph"><img src="https://agentmods.dev/badge/skills/robinoppenstam/claude-ralph/ralph.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 | $0.00000 | $0.00866 |
| Opus 5 | $0.00000 | $0.00433 |
| Sonnet 5 | $0.00000 | $0.00173 |
| Haiku 4.5 | $0.00000 | $0.00087 |
Grade A, and why
ralph 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 10d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ralph PRD Conversion Skill
This skill converts a markdown PRD into the JSON format that Ralph needs to run autonomously.
Usage
Load this skill and say: "Convert [path/to/prd.md] to prd.json"
Process
1. Read the Markdown PRD
Parse the PRD document and extract:
- Feature name
- User stories with their acceptance criteria
- Technical context
- Quality check commands
2. Generate Branch Name
Create a branch name following the pattern: ralph/[feature-name-kebab-case]
3. Determine Priority Order
Order stories by:
- Explicit priority if specified
- Dependencies (stories that others depend on come first)
- Order they appear in the document
4. Output JSON Format
Generate this structure:
{
"featureName": "Feature Name",
"branchName": "ralph/feature-name",
"description": "Brief description from PRD overview",
"userStories": [
{
"id": "US-001",
"title": "Story title",
"priority": 1,
"acceptanceCriteria": [
"Criterion 1",
"Criterion 2",
"typecheck passes",
"tests pass"
],
"passes": false,
"notes": "Any additional context"
}
],
"qualityChecks": {
"typecheck": "npm run typecheck",
"test": "npm test",
"lint": "npm run lint"
},
"techStack": {
"framework": "detected or specified",
"database": "detected or specified",
"testing": "detected or specified"
}
}
5. Save to prd.json
Save the output to: scripts/ralph/prd.json (or the ralph directory in your project)
Critical Conversion Rules
Story Size
- Each story must be small enough to complete in one context window
- If a story seems too large, suggest breaking it down
- Rule of thumb: If you need more than ~1000 tokens to explain it, it's too big
Acceptance Criteria
- Convert checkbox items to string array
- Always include quality checks:
- "typecheck passes" for TypeScript projects
- "tests pass" if tests are mentioned
- "lint passes" if linting is mentioned
- For UI stories, include "Verify in browser"
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.
- 10d ago First seen · 145 lines · 0 tokens per session scan A 999a906f63be
ralph is a skill published in the GitHub repository RobinOppenstam/claude-ralph (11 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 866 tokens. 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…