read-the-room

read-the-room is a cursor rule for Cursor from mohitagw15856/pm-claude-skills. It costs 127 tokens per session (1,050 once invoked), scanned A, original, MIT.

A guide to interpreting social situations by considering the mood, influence of different people, and meaning beneath what is said. Its conclusions are inferences, not certainties.

In plain words
What is it for?
Use it to assess meetings, group discussions, conflicts, and other situations where you need to decide when to speak, wait, build support, or change approach.
Why use it?
It helps when a conversation's real tension, goals, or decision-makers are unclear. It also encourages checking your interpretation before acting on it.

Cursor rule for Cursor

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

Good fit Use it to assess meetings, group discussions, conflicts, and other situations where you need to decide when to speak, wait, build support, or change approach.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/mohitagw15856/pm-claude-skills/read-the-room
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 read-the-room

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

Your own site · 80×15
<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/read-the-room"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/read-the-room.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 127 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,050 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 $0.00127 $0.01050
Opus 5 $0.00063 $0.00525
Sonnet 5 $0.00025 $0.00210
Haiku 4.5 $0.00013 $0.00105

Measured 12d ago against content hash d3b8e838edaa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

read-the-room 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 12d 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/read-the-room/read-the-room.mdc · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Read the Room

Some people instinctively sense the mood, the power dynamics, and what's really being said under the words — others miss it entirely and step on landmines. This helps you read a situation: from what you describe, it interprets the likely dynamics (the vibe, who's driving, the unspoken tension, what people actually want), tells you how to check your read against reality, and how to adjust — while cautioning that reading a room is inference, not certainty.

What This Skill Produces

  • The likely mood — the emotional temperature and vibe you might be missing (tense, checked-out, competitive, warm)
  • The power/influence map — who actually holds sway (not always the loudest or most senior), and whose buy-in matters
  • The unspoken layer — the tensions, subtext, and what people seem to actually want vs. what's being said
  • How to verify — ways to check your read (a test comment, a private ask, watching reactions) rather than acting on a guess
  • How to adjust — the change in your approach the read suggests (when to push, hold back, ally, or wait)
  • An over-reading caution — a reminder that inference isn't certainty and to stay curious, not paranoid

Required Inputs

Ask for these if not provided:

  • The situation — the meeting/gathering/interaction, and who's involved
  • What you've observed — reactions, tone, body language, what's been said (the raw signals)
  • Your position — your role/stake in it
  • What you're trying to do — the goal you're navigating toward
  • What's confusing you — where your read feels off or uncertain

Framework: Interpret, Verify, Adjust

  1. Read the emotional temperature. From the described signals, infer the likely mood — the thing that's felt but not said, which drives how people will actually respond.
  2. Map real influence. Identify who actually holds sway and whose reaction matters most — often not the person talking most or ranking highest.
  3. Surface the subtext. Name the likely unspoken tensions and what people seem to actually want, beneath the stated words.
  4. Hold it as a hypothesis. A read is a guess — offer ways to test it (a probing comment, a quiet check with someone, watching a reaction) before betting on it.
  5. Adjust the approach. Translate the read into a concrete change — push now vs. wait, whose buy-in to get first, what to avoid saying.
  6. Don't over-read. Caution against paranoia and elaborate mind-reading; stay curious and verify rather than assume the worst.

Read the full file on GitHub · 70 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. 12d ago First seen · 70 lines · 127 tokens per session scan A d3b8e838edaa

Subscribe to this mod's changes

read-the-room is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,357 stars, last pushed today), licensed MIT. It adds 127 tokens to every session and 1,050 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.