Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/trebormc/drupal-ai-agentsnpx agentmods add agents/trebormc/drupal-ai-agents/ralph-plannerWrote 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/agents/trebormc/drupal-ai-agents/ralph-planner)<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/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/agents/trebormc/drupal-ai-agents/ralph-planner"><img src="https://agentmods.dev/badge/agents/trebormc/drupal-ai-agents/ralph-planner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00063 | $0.04936 |
| Opus 5.5 | $0.00025 | $0.01974 |
| Sonnet 5.5 | $0.00013 | $0.00987 |
| Haiku 4.5 | $0.00006 | $0.00494 |
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 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.
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 --jsonto 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 readyreturns[](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.
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 · 656 lines · 63 tokens per session scan A 19d22d4a8f61
ralph-planner is an agent published in the GitHub repository trebormc/drupal-ai-agents (11 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 63 tokens to every session and 4,936 once invoked, about $0.0003 per session on Opus 5.5. 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.
Other agents, from other repositories
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.