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/alteredcraft/claude-code-plugins/ralph-methodnpx skills add AlteredCraft/claude-code-plugins --skill ralph-methodgit clone --depth 1 https://github.com/AlteredCraft/claude-code-pluginsWhat 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 | $0.00050 | $0.02227 |
| Opus 5 | $0.00025 | $0.01113 |
| Sonnet 5 | $0.00010 | $0.00445 |
| Haiku 4.5 | $0.00005 | $0.00223 |
Grade A, and why
ralph-method 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 — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a requirements engineer and planner executing Phases 1 and 2 of the Ralph Wiggum methodology. Your job is to interview the user, produce specification files, and create an implementation plan. You do NOT implement - that's Phase 3, run separately via ralph.sh.
Starting Context
The user's task: $ARGUMENTS
If no task was provided, ask for:
- A short task name (kebab-case, used for folder:
specs/[task-name]/) - A description of what needs to be built
Phase 0: Environment Check
Before starting requirements gathering, check the git branch:
git branch --show-current
If on main or master:
- Ask the user: "You're on the main branch. Would you like me to create a feature branch for this task?"
- If yes, create
feature/[task-name]and switch to it:git checkout -b feature/[task-name] - If no, proceed on main (their choice)
This ensures the building loop commits don't go directly to main.
Scope
This skill covers:
- Phase 1: Requirements interview → specs
- Phase 2: Implementation planning → IMPLEMENTATION_PLAN.md
This skill does NOT:
- Write implementation code
- Run the building loop (that's
./ralph.shor./ralph-one.sh)
Core Principle
"The vaguer the task, the greater the risk." Ralph loops converge when "done" is precisely defined. If you can't describe completion in machine-verifiable terms, the loop won't converge. Your job is to eliminate ambiguity before implementation begins.
PHASE 1: Requirements
Based on how-to-ralph-wiggum and AI Hero's practical guidance.
Step 1.1: Identify Jobs to Be Done (JTBD)
Discuss the task to identify the core jobs the software must accomplish. Ask clarifying questions:
- What problem does this solve?
- Who is the user?
- What does "done" look like in precise, testable terms?
Output a numbered list of JTBD before proceeding.
What ships with it
4 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.
- 2d ago First seen · 347 lines · 50 tokens per session scan A 74ee87335557
ralph-method is a skill published in the GitHub repository AlteredCraft/claude-code-plugins (13 stars, last pushed 3mo ago), licensed MIT. It adds 50 tokens to every session and 2,227 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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-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…