conflict-deescalation

conflict-deescalation is a cursor rule for Cursor from mohitagw15856/pm-claude-skills. It costs 126 tokens per session (1,107 once invoked), scanned A, original, MIT.

A guide for lowering tension during a heated disagreement, either in person or through messages. It focuses on understanding what is driving the conflict and finding a safe path toward resolution.

In plain words
What is it for?
It helps identify the underlying concern, choose calming words, avoid escalating language, and decide when to pause or disengage for safety.
Why use it?
It helps prevent defensive replies and attempts to prove who is right from making the disagreement worse.

Cursor rule for Cursor

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

Good fit It helps identify the underlying concern, choose calming words, avoid escalating language, and decide when to pause or disengage for safety.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/mohitagw15856/pm-claude-skills/conflict-deescalation
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 conflict-deescalation

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

Your own site · 80×15
<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/conflict-deescalation"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/conflict-deescalation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 126 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,107 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 $0.00126 $0.01107
Opus 5 $0.00063 $0.00553
Sonnet 5 $0.00025 $0.00221
Haiku 4.5 $0.00013 $0.00111

Measured 12d ago against content hash 94ff478ebc16, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

conflict-deescalation 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/conflict-deescalation/conflict-deescalation.mdc · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Conflict De-escalation

When a conflict is hot, nobody's thinking — you're both defending, not listening, and every reply pours fuel. Winning the point in that state loses the relationship. De-escalation is the skill of lowering the temperature first, so an actual resolution becomes possible. This reads what's really driving the heat, gives you the moves that calm it, and steers toward resolution once people can think again.

What This Skill Produces

  • The real driver — what's actually fueling the heat (usually an unmet need — to feel heard, respected, safe — under the surface argument)
  • The de-escalation moves — acknowledge the other person's feeling, slow the pace, lower your intensity, and find a shred of shared ground
  • What to say / what to avoid — the phrases that calm ("I hear that this matters to you") vs. the ones that escalate (defensiveness, "calm down," being right)
  • A path to resolution — how to move toward the actual issue once the temperature has dropped
  • A safety note — recognizing when to disengage entirely (it's not de-escalating, or there's a safety risk)

Required Inputs

Ask for these if not provided:

  • The conflict — what's happening, with whom, in person or in writing
  • What was said — the recent exchange, if you're mid-conflict
  • Your goal — calm it and resolve, calm it and pause, or exit safely
  • The stakes/relationship — who it's with and how much it matters
  • Your state — how activated you are (you may need to de-escalate yourself first)

Framework: Lower The Temperature Before The Point

  1. De-escalate yourself first. You can't calm a conflict while you're activated — a pause, a breath, and dropping your own intensity comes before anything.
  2. Find what's really driving it. The surface argument is rarely the real issue; underneath is usually a need to feel heard, respected, or safe. Address that.
  3. Acknowledge before you respond. Naming the other person's feeling ("I can see you're really frustrated") lowers defenses faster than any argument — people de-escalate when they feel heard.
  4. Slow down and soften. Lower your pace, volume, and intensity; the other person tends to mirror it. Avoid the escalators: defensiveness, "calm down," and needing to be right.
  5. Find shared ground. Even a small point of agreement shifts it from opponents to collaborators.
  6. Then move to the issue. Only once the heat drops, steer gently toward resolving the actual thing.
  7. Know when to disengage. If it won't cool, or there's any safety concern, exiting is the right move — say so.

Read the full file on GitHub · 72 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 · 72 lines · 126 tokens per session scan A 94ff478ebc16

Subscribe to this mod's changes

conflict-deescalation is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,357 stars, last pushed today), licensed MIT. It adds 126 tokens to every session and 1,107 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.