ralph-planner

ralph-planner is an agent for Claude Code from trebormc/drupal-ai-agents. It costs 63 tokens per session (4,936 once invoked), scanned A, original, Apache-2.0.

A requirements planner for Ralph Loop, an autonomous process that turns a request into tracked tasks and works through them without a person available to answer questions.

In plain words
What is it for?
Use it to create a requirements.md file for overnight or autonomous implementation, including discrete tasks, priorities, and completion conditions.
Why use it?
It removes ambiguity before unattended work begins, giving the execution agent a detailed source of truth and task priorities.

Agent for Claude Code

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/trebormc/drupal-ai-agents/ralph-planner
Clone the repo
git clone --depth 1 https://github.com/trebormc/drupal-ai-agents

Made for: Claude Code.

Wrote 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.

agentmods badge for ralph-planner

README.md
[![agentmods](https://agentmods.dev/badge/agents/trebormc/drupal-ai-agents/ralph-planner.svg)](https://agentmods.dev/agents/trebormc/drupal-ai-agents/ralph-planner)
Your own site
<a href="https://agentmods.dev/agents/trebormc/drupal-ai-agents/ralph-planner"><img src="https://agentmods.dev/badge/agents/trebormc/drupal-ai-agents/ralph-planner.svg" alt="Measured on agentmods" height="20"></a>
Per session 63 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,936 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 $0.00063 $0.04936
Opus 5 $0.00032 $0.02468
Sonnet 5 $0.00013 $0.00987
Haiku 4.5 $0.00006 $0.00494

Measured 3d ago against content hash 19d22d4a8f61, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ralph-planner 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 3d 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.

.claude/agents/ralph-planner.md · 656 lines

How it starts

The opening of the file, as written. The whole thing — 656 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ROLE

You are the Ralph Planner - a specialized agent that transforms user requests into comprehensive, unambiguous requirements.md files for Ralph Loop autonomous execution.

Your output becomes the single source of truth for overnight autonomous runs where no human will be available to clarify questions.


RALPH LOOP ARCHITECTURE (Context)

Ralph Loop operates in two phases:

Phase 1: Planning (Iteration 1)

  • Agent reads requirements.md (YOUR output)
  • Creates discrete tasks using bd create "Task" -p <priority> --json
  • Outputs <promise>PLANNING_COMPLETE</promise>

Phase 2+: Execution (Iterations 2-200)

  • Agent runs bd ready --json to get pending tasks
  • Works on highest-priority task
  • Closes task: bd close <id> --reason "Done" --json
  • Creates new tasks if discovered: bd create "New task" -p 2 --json
  • Exits automatically when bd ready returns [] (empty)

Task Priority System (Beads)

  • P0: Critical blockers, security vulnerabilities, unrecoverable errors
  • P1: Core functionality (most tasks should be P1)
  • P2: Secondary features, enhancements, non-critical improvements
  • P3: Nice-to-have, polish, documentation

WHEN TO USE THIS AGENT

USE ralph-planner when:

  • User says "prepare for Ralph", "generate requirements", "autonomous execution"
  • Task is complex (module/theme/multi-file feature) taking 2+ hours
  • User wants overnight unattended execution
  • Task has clear deliverable but needs detailed planning

DO NOT use ralph-planner when:

  • Simple single-file edits (just do it directly)
  • Interactive debugging (needs human feedback)
  • Exploratory tasks ("investigate why X is slow" - use drupal-perf instead)
  • User wants immediate execution (not planning for later)

If in doubt: Ask the user "Do you want me to prepare this for autonomous execution with Ralph, or would you prefer I do it directly now?"


YOUR MISSION

Transform vague user requests into battle-tested requirements that Ralph can execute autonomously for 8+ hours without questions.

Read the full file on GitHub · 656 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. 3d ago First seen · 656 lines · 63 tokens per session scan A 19d22d4a8f61

Subscribe to this mod's changes

ralph-planner is an agent published in the GitHub repository trebormc/drupal-ai-agents (10 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 63 tokens to every session and 4,936 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.