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/medical-appointment-advocate)<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/medical-appointment-advocate"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/medical-appointment-advocate/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/medical-appointment-advocate"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/medical-appointment-advocate.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 | $0.00137 | $0.01097 |
| Opus 5 | $0.00068 | $0.00549 |
| Sonnet 5 | $0.00027 | $0.00219 |
| Haiku 4.5 | $0.00014 | $0.00110 |
Grade A, and why
medical-appointment-advocate 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 9d 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.
Medical-Appointment Advocate
Medical appointments are short, stressful, and easy to leave without your real questions answered — especially when advocating for an aging parent or a sick family member. Good preparation changes the outcome: knowing what to raise first, what to bring, how to make sure you understood, and how to speak up when concerns get brushed off. This helps you walk in ready and walk out clear. It's navigation help, not medical advice.
What This Skill Produces
- A prioritized agenda — the concerns and questions to raise, ordered (appointments run short, so the most important thing comes first)
- What to bring — symptom history/timeline, current medications, past records, and specific questions written down
- Understanding tactics — note-taking, asking for plain-language explanations, and "teach-back" (repeating it back) to confirm you actually got it
- How to be heard — respectful ways to push if a concern is dismissed, ask "what else could this be?", and request next steps
- The before-you-leave checklist — the diagnosis/plan, medications, follow-up, warning signs, and who to call — confirmed before you walk out
- A boundary — this is advocacy/navigation support, not medical advice; the clinician is the authority
Required Inputs
Ask for these if not provided:
- Who & why — yourself or someone you care for, and the reason for the appointment
- The concerns — symptoms, questions, and worries to cover
- The history — relevant background, current meds, past visits
- The dynamic — new issue, ongoing condition, or a specialist referral
- Past frustrations — feeling rushed, dismissed, or confused before
Framework: Prepare, Understand, Confirm
- Prioritize the agenda. Appointments are short — lead with the most important concern and the questions that matter most, in case time runs out.
- Bring the information. A symptom timeline, a current medication list, relevant records, and written questions make the visit far more productive.
- Ensure understanding. Take notes, ask for plain-language explanations, and use teach-back ("so what I should do is...") to catch misunderstandings before leaving.
- Advocate respectfully. If a real concern is brushed off, it's okay to say "I'm still worried about X — what else could it be?" or ask for the reasoning; persistence, politely, gets you heard.
- Confirm before leaving. Lock down the diagnosis/plan, any medications and how to take them, the follow-up, the warning signs to watch, and who to contact — don't leave fuzzy.
- Stay in your lane. This helps you navigate and be heard; the clinician makes the medical calls.
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.
- 9d ago First seen · 71 lines · 137 tokens per session scan A 60817958d6b6
medical-appointment-advocate is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,357 stars, last pushed yesterday), licensed MIT. It adds 137 tokens to every session and 1,097 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
publisher
Publish HTML frontend projects to the publishing platform (publisher). Use when the user wants to publish/ship a project, get an access URL, list their published projects, or build an Android APK. No Python required — call the HTTP APIs directly.
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.