ralph-tasks

A converter that turns a product requirements document, or PRD, into prd.json files for Ralph, an autonomous software-building agent. It splits the requirements into small tasks with checks that can be verified.

In plain words
What is it for?
It is for converting PRDs written in text or Markdown into Ralph's JSON format. It creates focused stories and adds browser checks for interface work and unit-test checks for domain logic.
Why use it?
It makes a broad requirements document easier for an automated agent to execute safely. Specific acceptance checks clarify what must be true before each task is considered complete.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/wiggumdev/ralph/ralph-tasks
Any agent
npx skills add wiggumdev/ralph --skill ralph-tasks
Clone the repo
git clone --depth 1 https://github.com/wiggumdev/ralph

Made for: Claude Code, Codex.

Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,408 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 $0.00071 $0.01408
Opus 5 $0.00036 $0.00704
Sonnet 5 $0.00014 $0.00282
Haiku 4.5 $0.00007 $0.00141

Measured 2d ago against content hash ecf983a35095, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ralph-tasks 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.

packages/claude/skills/ralph-tasks/SKILL.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ralph PRD Converter

Converts existing PRDs to the prd.json format that Ralph uses for autonomous execution.


The Job

Goal: Generate a prd.json files where each item is small and specific.

CRITICAL: This is one of the most important phases. DO NOT SKIP.

Important: Acceptance criteria must be verifiable, not vague. "Works correctly" is bad. "Button shows confirmation dialog before deleting" is good. For any story with UI changes: Always include "Verify in browser using dev-browser skill" as acceptance criteria. This ensures visual verification of frontend work. For any story that includes domain logic: Always include "Verify with unit tests" as acceptance criteria.

Tracer Bullets

When building features, build a tiny, end-to-end slice of the feature first, seek feedback, then expand out from there.

Tracer bullets comes from the Pragmatic Programmer. When building systems, you want to write code that gets you feedback as quickly as possible. Tracer bullets are small slices of functionality that go through all layers of the system, allowing you to test and validate your approach early. This helps in identifying potential issues and ensures that the overall architecture is sound before investing significant time in development.


Output Format

Generate the PRD json based on the following json schema:

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "type": "array",
  "minItems": 1,
  "description": "Product Requirements Document: an array of features to be implemented by an LLM agent.",
  "items": {
    "type": "object",
    "required": ["category", "title", "description", "passes", "acceptance"],
    "properties": {
      "id": {
        "type": "string",
        "minLength": 1,
        "pattern": "^[a-z0-9-]+$",
        "description": "Unique identifier for cross-referencing (e.g., 'user-auth', 'api-rate-limiting'). Use lowercase with hyphens."
      },
      "category": {
        "type": "string",
        "minLength": 1,
        "description": "Feature category for grouping (e.g., 'Authentication', 'API', 'UI', 'Testing'). Helps locate related code."
      },
      "title": {
        "type": "string",
        "minLength": 1,
        "description": "Concise feature title (e.g., 'User Login', 'Rate Limiting Middleware'). Used in progress reports."
      },
      "description": {
        "type": "string",
        "minLength": 1,
        "description": "Detailed feature description explaining the expected behavior, user value, and any important context."
        "example": "User can log in with valid credentials"
      },
      "passes": {
        "type": "boolean",
        "description": "Completion status. Set to true only after implementation passes all acceptance criteria and tests."
      },
      "acceptance": {
        "type": "array",
        "minItems": 1,
        "description": "Acceptance criteria list. Each item should be independently verifiable. Write as assertions (e.g., 'Login form validates email format'). Describe creating tests or verifying in browser using dev-browser skill",
        "example": [
          "Login form validates email format",
          "Login form validates password length"
        ],
        "items": {
          "type": "string",
          "minLength": 1,
          "description": "A specific, testable criterion for feature completion"
        }
      },
      "priority": {
        "type": "string",
        "enum": ["critical", "high", "medium", "low"],
        "description": "Feature priority for ordering work. Defaults to 'medium' if not specified."
      },
      "dependencies": {
        "type": "array",
        "description": "Array of feature IDs that must pass before this feature can be started. Prevents working out of order.",
        "items": {
          "type": "string",
          "minLength": 1
        }
      },
      "technicalNotes": {
        "type": "string",
        "description": "Implementation hints: patterns to follow, libraries to use, constraints to respect (e.g., 'Use existing AuthService', 'Must support IE11')."
      },
      "testStrategy": {
        "type": "string",
        "description": "Testing guidance: test types needed (unit/integration/e2e), what to mock, edge cases to cover."
      },
      "outOfScope": {
        "type": "array",
        "description": "Explicit exclusions to prevent over-engineering (e.g., 'No OAuth support yet', 'Skip mobile responsive').",
        "items": {
          "type": "string",
          "minLength": 1
        }
      }
    },
    "additionalProperties": false
  }
}

Read the full file on GitHub · 154 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. 2d ago First seen · 154 lines · 71 tokens per session scan A ecf983a35095

Subscribe to this mod's changes

ralph-tasks is a skill published in the GitHub repository wiggumdev/ralph (19 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 71 tokens to every session and 1,408 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

use-agent-browser-for-airi

Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…

moeru-ai/airi · 87 tokens

opencli-sitemap-author

Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.

jackwener/OpenCLI · 67 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

peekaboo

Capture and automate macOS UI with the Peekaboo CLI.

the-open-agent/openagent · 17 tokens

repro-admin

Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.

emdash-cms/emdash · 48 tokens

browser_cdp

通过 Chrome DevTools Protocol (CDP) 连接已运行的浏览器,或扫描本机 CDP 端口,用于远程调试与多工具共享浏览器实例。.

mateaix/mateclaw · 44 tokens