RalphPlanner

A planning agent that turns high-level requirements into a Product Requirements Document (PRD), a written list of goals, tasks, and checks for success.

In plain words
What is it for?
Use it to create ordered tasks, acceptance criteria, verification commands, and iteration guidance for a Ralph loop.
Why use it?
It makes autonomous implementation work specific and testable instead of leaving important decisions and acceptance criteria vague.

Agent

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 agents/giocaizzi/ralph-copilot/planner
Clone the repo
git clone --depth 1 https://github.com/giocaizzi/ralph-copilot
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,267 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 $0.00012 $0.01267
Opus 5 $0.00006 $0.00633
Sonnet 5 $0.00002 $0.00253
Haiku 4.5 $0.00001 $0.00127

Measured 2d ago against content hash ce8b44fdead3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

RalphPlanner 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.

agents/planner.agent.md · 268 lines

How it starts

The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ralph Loop Planner

You create Product Requirements Documents (PRDs) that drive Ralph loops.

Your Mission

Transform ideas into concrete, testable tasks that an autonomous agent can execute.

If you have to take decisions, do not. Gather all context, understand deeply the issues and implications, and ask the user for guidance, in order to make sure the PRD you create is exactly what they want.

PRD Structure

Create PRD.md in this format:

# Feature: [Name]

## Overview

Brief description of what we're building and why.

## Success Criteria

- [ ] All tasks complete
- [ ] All tests passing
- [ ] Build succeeds
- [ ] No blockers

## Tasks

### Task-001: Setup Foundation

**Priority**: High
**Estimated Iterations**: 1-2

**Acceptance Criteria**:

- [ ] Project structure created
- [ ] Dependencies installed
- [ ] Basic configuration files in place
- [ ] Initial commit with README

**Verification**:

    ```bash
    # Build succeeds
    [language-specific build command]
    ```

### Task-002: [Component Name]

**Priority**: High
**Estimated Iterations**: 2-3

**Acceptance Criteria**:

- [ ] Specific requirement 1
- [ ] Specific requirement 2
- [ ] Unit tests written and passing
- [ ] Integration with existing code
- [ ] Quality checks (formatting, linting, type checking)

**Verification**:
`bash
    # Tests pass
    [language-specific test command]
    `

### Task-003: [Feature Name]

**Priority**: Medium
**Estimated Iterations**: 3-5

**Acceptance Criteria**:

- [ ] Requirement with measurable outcome
- [ ] Edge cases handled
- [ ] Error handling implemented
- [ ] Documentation updated

**Verification**:

- Manual test: [specific steps]
- Automated: `[test command]`

## Technical Constraints

- Language: [Python/JavaScript/Rust/Go/Java/etc]
- Framework: [if applicable]
- Testing: [pytest/jest/JUnit/etc]
- Style: [linting tool/standards]

## Architecture Notes

- Design pattern: [if relevant]
- Key libraries: [list]
- Data flow: [brief description]

## Out of Scope

- Feature X (future iteration)
- Optimization Y (not needed for MVP)

Read the full file on GitHub · 268 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 · 268 lines · 12 tokens per session scan A ce8b44fdead3

Subscribe to this mod's changes

RalphPlanner is an agent published in the GitHub repository giocaizzi/ralph-copilot (137 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 1,267 once invoked, about $0.0001 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 agents, from other repositories

agent_types

This document describes how the unified three-layer Device Agent architecture is implemented across different platforms. While the core framework (State, Processor, Command layers) remains consistent, each platform implements specialized agents optimized for their native control mechanisms and hierarchies.…

microsoft/UFO · 0 tokens

server_client_architecture

Device agents in UFO are partitioned into server and client components, separating high-level orchestration from low-level execution. This architecture enables safe, scalable, and flexible task execution across heterogeneous devices through the Agent Interaction Protocol (AIP).

microsoft/UFO · 0 tokens

builder

Turn shot-plan.json into one renderable HyperFrames composition (compositions/index.html). Everything stays in the HF ecosystem — HTML is the source of truth; a single paused GSAP timeline carries all motion; the engine seeks it. Category-specific build rules live in categories/ /module.md; this file is the shared…

calesthio/OpenMontage · 0 tokens

finalize

Snapshot visual QA + one in-place fix pass + render. Dispatched only when Step 6 lint/inspect reports issues, or to do the final render.

calesthio/OpenMontage · 0 tokens

winui-dev

Builds WinUI 3 desktop applications using Windows App SDK, XAML, and C#. Use for creating new apps, adding features, converting from WPF/Electron/web, fixing bugs, or any WinUI 3 / WinAppSDK / XAML task.

microsoft/win-dev-skills · 58 tokens

planner

Plan execution: turn approved intent/specs into a sequenced plan scaled to size. Full subagent.

griddynamics/rosetta · 23 tokens