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/long-term-care-options)<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/long-term-care-options"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/long-term-care-options/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/long-term-care-options"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/long-term-care-options.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 | $0.00149 | $0.01228 |
| Opus 5 | $0.00075 | $0.00614 |
| Sonnet 5 | $0.00030 | $0.00246 |
| Haiku 4.5 | $0.00015 | $0.00123 |
Grade A, and why
long-term-care-options 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 7d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Long-Term Care Options
Choosing care for an aging or ill loved one is one of the hardest decisions a family faces — emotionally fraught, expensive, and full of confusing options. This maps the landscape: what the main levels of care actually are and who each suits, how to match them to your person's real needs and budget, what to look for (and the red flags) when evaluating providers, and how to involve the person with dignity. It's a decision map, not medical or financial advice.
What This Skill Produces
- The options explained — the main levels in plain language: in-home care (from occasional help to live-in), adult day programs, assisted living, memory care, and nursing/skilled care — and who each is for
- A needs match — which options fit the person's actual care level (daily-living help vs. medical vs. dementia care), budget, and preferences
- Evaluation questions & red flags — what to ask and observe when touring/vetting providers (staffing, safety, cleanliness, culture, turnover, reviews, inspection records)
- Cost & funding to research — the (jurisdiction-specific) cost ranges and funding routes to look into, flagged to verify
- Involving the person — how to include them in the decision and preserve dignity, even when capacity is limited
- A boundary — this maps options; medical needs assessment and financial/legal specifics need professionals
Required Inputs
Ask for these if not provided:
- The person's needs — physical care, medical needs, cognitive status (dementia?), and how much help daily
- Their wishes — what they want, and their capacity to be involved
- The family situation — who's available, proximity, and the budget
- The trigger — a health change, a crisis, safety concerns, or planning ahead
- Region — for the (educational) cost/funding pointers
Framework: Match Need To Level, Vet Carefully
- Explain the levels clearly. From in-home help through assisted living to nursing care, describe what each provides and the kind of need it suits — the terms confuse everyone.
- Match to real needs. The right option depends on care level (help with daily living vs. skilled medical vs. memory care), not just preference or cost — assess honestly.
- Weigh the trade-offs. In-home preserves familiarity but has limits; facilities offer more support but are a big change — surface the trade-offs for this person.
- Vet providers hard. Give the questions and red flags: staffing ratios and turnover, safety and cleanliness, the culture/warmth, reviews, and any inspection/regulatory records.
- Research cost and funding. Costs are high and funding is jurisdiction-specific — point to the ranges and funding routes to investigate, flagged to verify locally.
- Involve the person with dignity. Include them as much as their capacity allows; this is their life. And bring in professional assessment for medical/financial/legal specifics.
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.
- 7d ago First seen · 78 lines · 149 tokens per session scan A a2e9f668a717
long-term-care-options is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,352 stars, last pushed 3d ago), licensed MIT. It adds 149 tokens to every session and 1,228 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.