ralplan

ralplan is a cursor rule for coding agents from dasomel/oh-my-cursor. It costs 20 tokens per session (414 once invoked), scanned A, original, MIT.

A planning process where a proposed software plan is reviewed by an architect and a critic, then revised until they agree. It stores each review round in a plan file.

In plain words
What is it for?
It is for preparing software plans that need feasibility checks, critical review, testable acceptance criteria, and user approval.
Why use it?
It helps uncover design problems, missing requirements, untested assumptions, and unhandled risks before implementation starts.

Cursor rule

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 rules/dasomel/oh-my-cursor/ralplan
Clone the repo
git clone --depth 1 https://github.com/dasomel/oh-my-cursor

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 ralplan

README.md
[![agentmods](https://agentmods.dev/badge/rules/dasomel/oh-my-cursor/ralplan.svg)](https://agentmods.dev/rules/dasomel/oh-my-cursor/ralplan)
Your own site
<a href="https://agentmods.dev/rules/dasomel/oh-my-cursor/ralplan"><img src="https://agentmods.dev/badge/rules/dasomel/oh-my-cursor/ralplan.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 414 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 $0.00020 $0.00414
Opus 5 $0.00010 $0.00207
Sonnet 5 $0.00004 $0.00083
Haiku 4.5 $0.00002 $0.00041

Measured 3d ago against content hash 4f278124496f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ralplan 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.

rules/workflows/ralplan.mdc · 72 lines

What it actually says

Ralplan Workflow

Iterative planning with consensus — Planner proposes, Architect evaluates, Critic challenges, repeat until consensus.

Trigger Keywords

"ralplan", "consensus plan", "plan with review"

Process

Round 1:
  [Planner]   → Create initial plan → .omc-cursor/plans/{task}.md
  [Architect] → Evaluate feasibility, design concerns
  [Critic]    → Challenge assumptions, find gaps

  If concerns exist → Planner revises plan

Round 2:
  [Planner]   → Revised plan incorporating feedback
  [Architect] → Re-evaluate
  [Critic]    → Re-challenge

  Repeat until: All roles agree (max 3 rounds)

Final:
  Present consensus plan to user → Await approval

Consensus Criteria

A plan reaches consensus when:

  • Architect confirms feasibility and sound design
  • Critic has no HIGH-severity concerns remaining
  • All acceptance criteria are testable
  • Risk mitigations are defined for identified risks

Output

Each round updates .omc-cursor/plans/{task}.md with:

# Plan: {task}

## Round {N} — {status: DRAFT / REVISED / CONSENSUS}

### Plan
{steps}

### Architect Feedback
{feasibility assessment}

### Critic Feedback
{concerns with severity}

### Changes from Previous Round
{what was revised and why}

Rules

  • Maximum 3 rounds — if no consensus, present best version with noted disagreements
  • Each role must provide concrete, actionable feedback
  • Planner must address every HIGH concern in revision
  • Don't over-plan — stop when the plan is "good enough to start"
  • Announce role transitions: "Round 2: Switching to Architect role for feasibility review."
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 · 72 lines · 20 tokens per session scan A 4f278124496f

Subscribe to this mod's changes

ralplan is a cursor rule published in the GitHub repository dasomel/oh-my-cursor (2 stars, last pushed 5mo ago), licensed MIT. It adds 20 tokens to every session and 414 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 2026-08-31.