Ralph Orchestrator is a framework that repeatedly runs AI-agent tasks until they finish or reach an iteration limit. Developers use it to coordinate autonomous coding work through command-line, web-dashboard, and MCP-server interfaces, with state managed per workspace. The catalogue entries provide agent skills, agents, instructions, and plugins for operating Ralph.
Borrowing it
Nothing to install: this file belongs to mikeyobrien/ralph-orchestrator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mikeyobrien/ralph-orchestrator/main/.claude/skills/pdd/SKILL.mdgit clone --depth 1 https://github.com/mikeyobrien/ralph-orchestratorWrote 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/mikeyobrien/ralph-orchestrator/pdd)<a href="https://agentmods.dev/skills/mikeyobrien/ralph-orchestrator/pdd"><img src="https://agentmods.dev/badge/skills/mikeyobrien/ralph-orchestrator/pdd/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/mikeyobrien/ralph-orchestrator/pdd"><img src="https://agentmods.dev/badge/skills/mikeyobrien/ralph-orchestrator/pdd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00034 | $0.01679 |
| Opus 5.5 | $0.00014 | $0.00672 |
| Sonnet 5.5 | $0.00007 | $0.00336 |
| Haiku 4.5 | $0.00003 | $0.00168 |
Grade A, and why
pdd 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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- pdd — 89% identical, 28 lines differ
How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt-Driven Development
Overview
Transform a rough idea into a detailed design with an implementation plan. The process is iterative: clarify requirements, research, design, plan — moving between phases as needed.
Important Notes
These rules apply across ALL steps:
- User-driven flow: Never proceed to the next step without explicit user confirmation. At each transition, ask the user what they want to do next.
- Iterative: The user can move between requirements clarification and research at any time. Always offer this option at phase transitions.
- Record as you go: Append questions, answers, and findings to project files in real time — don't batch-write at the end.
- Mermaid diagrams: Include diagrams for architectures, data flows, and component relationships in research and design documents.
- Sources: Cite references and links in research documents when based on external materials.
- Planning only: This SOP produces planning artifacts. You MUST NOT implement code, run containers, execute scripts, or begin any implementation work. If the user wants implementation, direct them to
ralph run.
Parameters
- rough_idea (required): The initial concept or idea to develop
- project_dir (optional, default:
specs/{task_name}/): Base directory for all artifacts.{task_name}is derived as kebab-case from the idea (e.g., "build a rate limiter" →rate-limiter). Aligns with Ralph's spec-driven pipeline.
Constraints:
- You MUST ask for all required parameters upfront in a single prompt
- You MUST support multiple input methods: direct text, file path, URL
- You MUST derive
task_namefrom the rough idea as kebab-case - You MUST NOT overwrite an existing project directory — ask for a new path if it already has contents
Steps
1. Create Project Structure
Create the directory and initial files:
{project_dir}/rough-idea.md— the provided rough idea{project_dir}/requirements.md— Q&A record (initially empty){project_dir}/research/— directory for research notes
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.
- 1mo ago First seen · 168 lines · 34 tokens per session scan A eaf6a041272a
pdd is a skill published in the GitHub repository mikeyobrien/ralph-orchestrator (3,186 stars, last pushed 9d ago), licensed MIT. It adds 34 tokens to every session and 1,679 once invoked, about $0.0001 per session on Opus 5.5. 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
jetbrains-session
Use when working on the JetBrains chat session UI or SessionModel/SessionController — transcript cards, retained Swing lifecycle, session background surfaces, editor-derived styling, adding session events, and session/controller testing with FakeSessionRpcApi.
chart
Use when the user asks to visualize data with charts, graphs, or plots using the chart tool (bar, line, scatter, pie, time series, etc.).
contentful-cms
Contentful content types, GraphQL/REST queries, CLI migrations, assets and locales. Use when changing a Contentful content model, querying Contentful, or migrating its content.
refactor-planner
Plan safe refactoring with dependency analysis, impact assessment, and rollback strategies.
hydra
Multi-agent orchestration framework for Claude Code. Automatically delegates tasks to cheaper, faster sub-agents (Haiku, Sonnet) while maintaining Opus-level quality through verification. Use when working on any coding task — Hydra activates automatically to route file exploration, test running, documentation, code…
alibaba-maestro
Alibaba Cloud Maestro routing skill. Classify the user's Alibaba Cloud task, select the narrowest specialist agent or the right team of specialists from the catalog, and dispatch them — single specialist for focused tasks, parallel team (max 4) for multi-domain tasks. Never auto-dispatch live-guard agents.…