repair-after-a-fight

repair-after-a-fight is a cursor rule for Cursor from mohitagw15856/pm-claude-skills. It costs 123 tokens per session (1,076 once invoked), scanned A, original, MIT.

A guide to repairing a relationship after an argument by reconnecting, acknowledging harm, and rebuilding trust.

In plain words
What is it for?
Use it to identify what really needs repair, reopen the conversation, take responsibility for your part, recognize the other person's hurt, and agree on how to move forward.
Why use it?
It helps prevent silence and resentment from making the damage worse, while avoiding defensive or empty apologies.

Cursor rule for Cursor

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

Good fit Use it to identify what really needs repair, reopen the conversation, take responsibility for your part, recognize the other person's hurt, and agree on how to move forward.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/mohitagw15856/pm-claude-skills/repair-after-a-fight
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 repair-after-a-fight

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

Your own site · 80×15
<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/repair-after-a-fight"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/repair-after-a-fight.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 1,076 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 $0.01076
Opus 5 $0.00062 $0.00538
Sonnet 5 $0.00025 $0.00215
Haiku 4.5 $0.00012 $0.00108

Measured 13d ago against content hash 42fbc8266334, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

repair-after-a-fight 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/repair-after-a-fight/repair-after-a-fight.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.

Repair After a Fight

Every relationship has fights — what separates the strong ones isn't never fighting, it's repairing well afterward. Left unrepaired, the silence hardens and the resentment compounds. This helps you reconnect: figure out what actually needs mending, own your part specifically (not a defensive non-apology), acknowledge their hurt, and rebuild trust — because the repair is where the relationship is actually made or broken.

What This Skill Produces

  • What needs repairing — separating the surface incident from the deeper hurt underneath (often "you didn't have my back" matters more than the topic)
  • A genuine repair approach — owning your specific part, acknowledging their feelings, and a real (not defensive or "sorry you feel") apology where warranted
  • The reopening words — how to break the silence and start the repair without reigniting the fight
  • The rebuild — moving from "okay we're past it" to actually restoring trust and understanding what happened
  • A both-sides note — repair usually needs each person to own their part; how to do yours without demanding theirs

Required Inputs

Ask for these if not provided:

  • The fight — what it was about and what was said/done
  • Your part — honestly, what you contributed (defensiveness here blocks repair)
  • The relationship — partner, friend, family, and how it usually goes
  • Where it stands — cold silence, a tense truce, or still raw
  • Your goal — genuinely repair, or just end the standoff

Framework: Reconnect, Own, Rebuild

  1. Find the real hurt. The topic of the fight is often not the wound — underneath is usually feeling unheard, disrespected, or unsupported. Repair the real thing.
  2. Own your part specifically. A genuine "I was wrong to X, and I can see it hurt you" repairs; a defensive "I'm sorry but you..." or "sorry you feel that way" makes it worse. Take your actual part.
  3. Acknowledge their hurt. Show you understand how it landed for them, without rushing to defend or explain — feeling understood is most of repair.
  4. Reopen without reigniting. Break the silence with warmth and ownership, not a re-litigation of who was right.
  5. Rebuild, don't just bury. Move past "let's forget it" toward actually understanding what happened and how to handle it better — that's what restores trust.
  6. Do your part regardless. You can own your side without them owning theirs; leading the repair often unlocks theirs, but don't make yours conditional.

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. 13d ago First seen · 70 lines · 123 tokens per session scan A 42fbc8266334

Subscribe to this mod's changes

repair-after-a-fight 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 1,076 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.