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.
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.
git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skillsWrote 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.
[](https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/end-of-life-wishes-conversation)<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/end-of-life-wishes-conversation"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/end-of-life-wishes-conversation/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.
<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/end-of-life-wishes-conversation"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/end-of-life-wishes-conversation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00133 | $0.01236 |
| Opus 5 | $0.00067 | $0.00618 |
| Sonnet 5 | $0.00027 | $0.00247 |
| Haiku 4.5 | $0.00013 | $0.00124 |
Grade A, and why
end-of-life-wishes-conversation 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
End-of-Life Wishes Conversation
The conversation nobody wants to have is the one that, unhad, leaves families guessing and guilt-ridden during a crisis — making wrenching decisions with no idea what their loved one would have wanted. Having it before a crisis, gently and thoroughly, is one of the greatest gifts a family can give each other. This helps you open it without it feeling morbid, cover what matters, listen well, and capture the wishes so they can actually be honored. Not legal or medical advice.
What This Skill Produces
- A gentle opening — a way to start this conversation that doesn't feel morbid, forced, or like you're rushing them toward death (a news story, a form to fill, "I want to make sure we honor what you want")
- The areas to cover — medical wishes (interventions, resuscitation, comfort vs. aggressive care), where they want to be cared for and to die, what quality of life means to them, spiritual/personal wishes, and the practical/legal pieces (documents, who decides)
- A listen-don't-impose stance — how to draw out their wishes rather than project your own or steer them
- How to handle resistance — if they don't want to talk about it, how to ease in without forcing
- Capturing & sharing it — how to document the wishes and make sure the right people (family, doctors) know them, and a nudge toward proper advance-directive documents
- A boundary — this guides the conversation; the legal documents and medical specifics need professionals
Required Inputs
Ask for these if not provided:
- Who — whose wishes (an aging parent, an ill partner, planning your own)
- The context — proactive planning, a recent diagnosis, or declining health
- The relationship & dynamic — how open they are, and whether this is welcome or resisted
- What prompted it — and any urgency
- What's been discussed — any wishes already known or documented
Framework: Open Gently, Listen, Capture
- Open without morbidity. Frame it as honoring their wishes and easing the family's burden — anchored to a prompt (a form, a story, a relative's experience) so it's not out of nowhere. Reassure it's about respecting them, not giving up on them.
- Cover the real areas. Medical interventions and comfort-vs-aggressive care, where they want to be, what makes life worth living for them, spiritual/personal wishes, and the practical/legal (documents, decision-maker).
- Listen, don't impose. This is about their wishes — draw them out with open questions and resist steering toward what you'd want or find easier.
- Ease resistance. If they deflect, don't force it — plant the seed, come back another time, or start with the easier practical pieces.
- Capture and share. Write down what they express, make sure the key people and their doctors know, and point them toward proper advance-directive/legal documents so wishes are actually binding.
- Get the documents right. The conversation isn't the paperwork — flag that legal directives and medical orders need the proper professional process.
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.
- 8d ago First seen · 71 lines · 133 tokens per session scan A 90b9dbd03a5d
end-of-life-wishes-conversation is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,357 stars, last pushed yesterday), licensed MIT. It adds 133 tokens to every session and 1,236 once invoked, about $0.0007 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 2026-09-03.
Other cursor rules, from other repositories
cursor
Always-on my-adhd-caveman. Off with "stop adhd-caveman" or "normal mode".
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.