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/care-team-coordinator)<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/care-team-coordinator"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/care-team-coordinator/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/care-team-coordinator"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/care-team-coordinator.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 | $0.00130 | $0.01095 |
| Opus 5 | $0.00065 | $0.00548 |
| Sonnet 5 | $0.00026 | $0.00219 |
| Haiku 4.5 | $0.00013 | $0.00110 |
Grade A, and why
care-team-coordinator 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Care-Team Coordinator
Caring for someone rarely fails from lack of love — it fails from disorganization: information scattered, tasks defaulting to one exhausted person, family out of sync, and things slipping through the cracks. This turns it into a coordinated effort: who does what, a shared source of truth for the important information, a fair division of tasks, and a communication rhythm — so the care is reliable and the load is shared.
What This Skill Produces
- The who-does-what map — the roles across medical (appointments, meds), daily (meals, transport, errands), financial/admin, and emotional support, and who owns each
- A shared-information system — one accessible place for the key info (medications, doctors, contacts, schedule, wishes) so everyone's working from the same page
- A fair task division — a way to split the load among family/helpers so it doesn't all fall on one person (the classic caregiving failure)
- A communication rhythm — how the team stays in sync (a group chat, a shared doc, a regular check-in) without constant chaos
- The single source of truth — keeping the critical information (meds, allergies, contacts, care wishes) current and reachable in an emergency
Required Inputs
Ask for these if not provided:
- Who's being cared for — and their needs (medical, mobility, cognitive, daily living)
- The people available — family, friends, paid helpers, and their capacities/locations
- The current state — what's happening now and where it's breaking down
- The main gaps — what keeps falling through, and who's overloaded
- Tools you'd use — a shared app, group chat, doc, or paper
Framework: Map, Share, Divide, Sync
- Map the care needs and roles. List everything care involves (medical, daily, admin, emotional) and assign clear ownership — unassigned tasks are the ones that get dropped.
- Create one source of truth. Put the critical information — medications, doctors, contacts, schedule, and care wishes — somewhere the whole team can access, so no one's guessing.
- Divide the load fairly. Split tasks among the available people by capacity and location; explicitly avoid dumping it all on one person (usually the nearest or the daughter).
- Set a communication rhythm. A shared channel and a regular check-in keep everyone in sync and surface problems early — without a hundred scattered messages.
- Keep it current and reachable. The key info must be up to date and accessible in an emergency (meds, allergies, contacts, directives) — assign someone to maintain it.
- Include the caregiver. Coordinate support for the primary caregiver too, not just the person being cared for.
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 · 75 lines · 130 tokens per session scan A 52eb2fe1672e
care-team-coordinator is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,352 stars, last pushed 3d ago), licensed MIT. It adds 130 tokens to every session and 1,095 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 2026-09-03.
Other cursor rules, from other repositories
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.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.