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/fagnerjs/ralphi/ralphnpx skills add fagnerjs/ralphi --skill ralphgit clone --depth 1 https://github.com/fagnerjs/ralphiWhat 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 | $0.00065 | $0.01760 |
| Opus 5 | $0.00032 | $0.00880 |
| Sonnet 5 | $0.00013 | $0.00352 |
| Haiku 4.5 | $0.00006 | $0.00176 |
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 2d 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 — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ralph JSON Converter
Turn an existing PRD into the prd.json document Ralph uses to drive autonomous execution.
Goal
Take a PRD in Markdown or plain text and produce prd.json inside the Ralph workspace.
Required Output Shape
Use this structure:
{
"project": "[Project Name]",
"branchName": "ralph/[feature-name-kebab-case]",
"description": "[Short feature summary based on the PRD]",
"userStories": [
{
"id": "US-001",
"title": "[Story title]",
"description": "As a [user], I want [capability] so that [benefit]",
"acceptanceCriteria": [
"Criterion 1",
"Criterion 2",
"Typecheck passes"
],
"priority": 1,
"passes": false,
"notes": ""
}
]
}
Most Important Rule: Keep Stories Small
Every story must fit within a single Ralph iteration.
Ralph starts each iteration with a fresh Amp session. If a story spans too much code or too many concerns, the model is likely to lose context and leave the work incomplete.
Good story sizes
- Add one database field plus its migration
- Add one focused backend behavior
- Add one UI element to an existing screen
- Add one filter or control to an existing list
Stories that are too large
Break down items like these:
- "Build the whole dashboard"
- "Add authentication"
- "Refactor the API"
Instead, split them into smaller steps such as schema work, backend logic, UI pieces, and follow-up interactions.
Practical rule: if the change cannot be explained clearly in 2-3 sentences, split it further.
Order Stories by Dependency
Ralph executes stories according to priority. Earlier work must unlock later work, not depend on it.
Preferred order
- Database or schema changes
- Backend or server-side behavior
- UI work that depends on the backend
- Summary, reporting, or aggregation views
Avoid this pattern
- UI story that assumes missing backend or schema support
- Supporting backend/schema story that should have come first
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.
- 2d ago First seen · 272 lines · 65 tokens per session scan A 303d23d54286
ralph is a skill published in the GitHub repository fagnerjs/ralphi (6 stars, last pushed 5mo ago), licensed MIT. It adds 65 tokens to every session and 1,760 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
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…