rabbit-hole-rescue

rabbit-hole-rescue is a cursor rule for Cursor from mohitagw15856/pm-claude-skills. It costs 123 tokens per session (1,541 once invoked), scanned A, original, MIT.

A conversation guide for talking with someone who believes conspiracy theories, false information, or extremist ideas. It focuses on keeping trust and inviting reflection instead of trying to win an argument.

In plain words
What is it for?
Planning conversations with a family member or friend who has become absorbed in misleading or extreme beliefs. It suggests questions, supportive ways to engage, and reactions to avoid.
Why use it?
Mocking someone or overwhelming them with corrections can make them defensive and more committed to the belief. It helps preserve a relationship so honest conversation remains possible.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc).

Good fit Planning conversations with a family member or friend who has become absorbed in misleading or extreme beliefs. It suggests questions, supportive ways to engage, and reactions to avoid.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/mohitagw15856/pm-claude-skills/rabbit-hole-rescue
About the project

PM Skills is a collection of plain-Markdown instructions that teach AI assistants structured methods for handling professional, personal, and life-admin tasks. People use it with Claude, ChatGPT, Gemini, Cursor, Codex, and other supported agents for work such as writing product requirements, reviewing documents, or planning difficult situations.

mohitagw15856/pm-claude-skills · 1,357 stars · on GitHub · mohitagw15856.github.io

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.

Clone the repo
git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills

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 rabbit-hole-rescue

README.md
[![agentmods](https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/rabbit-hole-rescue/github.svg)](https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/rabbit-hole-rescue)
Your own site
<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/rabbit-hole-rescue"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/rabbit-hole-rescue/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.

agentmods 80×15 button for rabbit-hole-rescue

Your own site · 80×15
<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/rabbit-hole-rescue"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/rabbit-hole-rescue.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 123 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,541 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00123 $0.01541
Opus 5 $0.00062 $0.00771
Sonnet 5 $0.00025 $0.00308
Haiku 4.5 $0.00012 $0.00154

Measured 13d ago against content hash 831e4ac2ae42, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

rabbit-hole-rescue 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 13d 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.

exports/cursor/other/rabbit-hole-rescue/rabbit-hole-rescue.mdc · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rabbit Hole Rescue Skill

Watching someone you love disappear into conspiracy theories, misinformation, or extremism is uniquely painful, and almost everything instinct tells you to do — send the debunk, argue the facts, mock the belief — makes it worse, because the belief isn't really about facts. It's usually meeting a need: belonging, certainty, feeling special or in-the-know, a sense of control in a scary world. This skill drops the losing game of fact-warfare and runs the approach researchers and exit-counselors actually use: preserve the relationship (your influence lives entirely in the relationship), stay curious instead of combative, and plant small doubts rather than demand surrender. The realistic goal isn't winning the argument tonight — it's keeping the door open so they have somewhere to come back to.

What This Skill Produces

  • A conversation approach for the specific person: how to engage the belief without attacking them, the questions that invite reflection instead of defense, and how to affirm the relationship even across the divide
  • A what-not-to-do list: the instinctive moves (debunk-dumping, ridicule, ultimatums, "how can you believe that") that entrench them, and why each backfires
  • A realistic goal-set: staged and honest — keep the relationship, keep the door open, plant a doubt, understand the underlying need — instead of the fantasy of a single conversation that snaps them out of it
  • Your own boundaries and wellbeing: what to do when the belief is hateful or the conversations are hurting you — because keeping the door open never means accepting abuse or dehydrating yourself trying to save them

Required Inputs

Ask for (if not already provided):

  • Who it is, the relationship, and how far in they are (dabbling vs deep, and whether it's harming them or others)
  • What they believe and — importantly — what you think it's doing for them (belonging? certainty? feeling important? fear?)
  • What's been tried and how it went (usually arguing; usually badly)
  • What the user actually wants and can sustain — and where their own limits are (hateful content, their own mental health)

Read the full file on GitHub · 124 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. 13d ago First seen · 124 lines · 123 tokens per session scan A 831e4ac2ae42

Subscribe to this mod's changes

rabbit-hole-rescue is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,357 stars, last pushed yesterday), licensed MIT. It adds 123 tokens to every session and 1,541 once invoked, about $0.0006 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 2026-08-30.