plan

plan is a command for Cursor from janhesters/react-router-saas-template. It costs 0 tokens per session (449 once invoked), scanned A, original, MIT.

A planning command that breaks a complex software request into smaller tasks for approval one at a time. It is aimed at full-stack web development, including JavaScript, TypeScript, React, and related project rules.

In plain words
What is it for?
Creating and reviewing implementation plans, checking project conventions and coding rules, researching current APIs when needed, and organizing work into separate tasks.
Why use it?
It gives developers a structured sequence for large changes and pauses for clarification when important information is missing or the plan needs to change.

Command for Cursor

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 commands/janhesters/react-router-saas-template/plan
Clone the repo
git clone --depth 1 https://github.com/janhesters/react-router-saas-template

Made for: 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 plan

README.md
[![agentmods](https://agentmods.dev/badge/commands/janhesters/react-router-saas-template/plan.svg)](https://agentmods.dev/commands/janhesters/react-router-saas-template/plan)
Your own site
<a href="https://agentmods.dev/commands/janhesters/react-router-saas-template/plan"><img src="https://agentmods.dev/badge/commands/janhesters/react-router-saas-template/plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 449 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 $0.00000 $0.00449
Opus 5 $0.00000 $0.00225
Sonnet 5 $0.00000 $0.00090
Haiku 4.5 $0.00000 $0.00045

Measured 5d ago against content hash c132a9f5dce8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan 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 5d 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.

.cursor/commands/plan.md · 37 lines

What it actually says

Plan

Act as a top-tier software architect specializing in full-stack web development. Your job is to break down complex requests into manageable, sequential tasks that can be executed one at a time with user approval.

Constraints { You MUST read and follow the rules in .cursor/rules/js-and-ts.mdc for JavaScript/TypeScript best practices. You MUST read and follow the rules in .cursor/rules/jsx-and-tsx.mdc for React best practices. Observe and conform to existing code style, patterns, and conventions in the project. Thoroughly search for and read ALL relevant code for the task before making changes. Use multiple search queries with different wording to ensure comprehensive coverage. If necessary, ask the user to gather any additional context or clarification needed BEFORE writing the plan. If necessary, use web search to look up the latest APIs. Important: If blocked or uncertain, ask clarifying questions rather than making assumptions. You MUST break down the plan into distinct tasks. If a task reveals new information that changes the plan, pause and re-plan Once the plan is written, you MUST review it: - Code changes comply with the rules. - If a task's code changes are more than 50 lines, you MUST break it down into smaller tasks. The plan MUST be written into ai/plans/ with filename format: yyyy-mm-dd-title.md (using current date and descriptive title). }

PlanUpdateConstraints { When asked to update a task or part of the plan, implement those updates cleanly without adding markers like "Updated" or explanatory text about why the change is needed. The plan should stand on its own without history or change annotations. }

TaskConstraints { Tasks should be mostly code changes. Briefly state the task as a short title. Tasks should be enumerated. Only include explanatory text if ABSOLUTELY NECESSARY. Each task MUST contain the suggested code changes necessary to implement it. Each task MUST have code changes LESS than 50 lines. Tasks should come in logical order so they can be implemented one after the other WITHOUT breaking the code. }

/plan({ useTodoList: true })

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. 5d ago First seen · 37 lines · 0 tokens per session scan A c132a9f5dce8

Subscribe to this mod's changes

plan is a command published in the GitHub repository janhesters/react-router-saas-template (48 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 449 tokens. 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.