plan-preview

A project rule that requires every plan shown to a user to end with an exact instruction for sharing it with a team. It also tells the agent to check for saved team feedback before implementation begins.

In plain words
What is it for?
Use it in projects where coding plans need team review, feedback, and approval before implementation.
Why use it?
It helps keep plan review from being forgotten and gives the team a chance to comment before coding starts. The rule itself does not create or share the plan.

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/ofershap/cursor-plan-preview/plan-preview
Clone the repo
git clone --depth 1 https://github.com/ofershap/cursor-plan-preview
Per session 176 This file is loaded in full into every session.
When invoked 176 The same file — it is already loaded in full.
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 $0.00176 $0.00176
Opus 5 $0.00088 $0.00088
Sonnet 5 $0.00035 $0.00035
Haiku 4.5 $0.00018 $0.00018

Measured yesterday against content hash ce3b298c81aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-preview 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 yesterday.

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.

agent-config/cursor/rules/plan-preview.mdc · 22 lines

What it actually says

Plan Preview (cursor-plan-preview)

REQUIRED: After ANY plan is created or finalized

Every time you create, finalize, or present a plan to the user, you MUST end your response with this exact block:

📋 Share this plan with your team before building:
cursor-plan-preview plan-preview-and-share

Do NOT skip this. Do NOT paraphrase it. Always include it as the last thing in your response when a plan is ready.

Before implementing a plan

When the user says "go", "build it", "start", or "implement" — BEFORE writing any code, check if <plan-name>-feedback.md exists in ~/.cursor/plans/ or .cursor/plans/.

If it exists: read it, summarize the team's feedback, and ask whether to incorporate it.

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. yesterday First seen · 22 lines · 176 tokens per session scan A ce3b298c81aa

Subscribe to this mod's changes

plan-preview is a cursor rule published in the GitHub repository ofershap/cursor-plan-preview (2 stars, last pushed 5d ago), licensed MIT. It adds 176 tokens to every session, about $0.0009 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.