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/grief-admin)<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/grief-admin"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/grief-admin/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/grief-admin"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/grief-admin.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 | $0.01554 |
| Opus 5 | $0.00065 | $0.00777 |
| Sonnet 5 | $0.00026 | $0.00311 |
| Haiku 4.5 | $0.00013 | $0.00155 |
Grade A, and why
grief-admin 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 10d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grief Admin Skill
Grief arrives with a second job: dozens of phone calls, forms, and account closures, each requiring you to say "they've died" again to a stranger — and it lands exactly when you have the least capacity to do any of it. Most guides make this worse by dumping an overwhelming master checklist. This one triages: what truly can't wait (days), what should happen soon (weeks), and the large majority that can genuinely wait months — because almost nothing on the list is as urgent as the internet implies, and permission to do it slowly is part of the help. It handles the humane logistics and points clearly at the parts that need a professional.
What This Skill Produces
- A triaged task list: 🔴 urgent (days) · 🟡 soon (weeks) · 🟢 whenever (months, and that's fine) — so you're not carrying the whole thing at once
- Notification scripts: the short, kind phone/email lines for banks, employers, utilities, subscriptions, so you don't have to compose "they died" thirty times
- A who-to-tell-and-close list built for this person's actual life (accounts, services, memberships, the digital ones people forget)
- A do-it-in-pieces sequence: the order that reduces stress, with the explicit standing permission to pause, delegate, and leave the 🟢 pile for later
- Clear hand-offs to the professional bits (probate/estate, tax, benefits) without pretending to be them
Required Inputs
Ask for (if not already provided):
- The relationship to the person and the rough shape of their life (worked? rented/ owned? married/partnered? dependents? online life?)
- What's already been handled (death certificate, funeral) and what's looming
- The user's own state and support — are they doing this alone, exhausted, able to delegate any of it?
- Country/region, so the professional-process pointers (registration, probate, benefits) route correctly — flagged for local verification, not asserted
Framework
- Triage hard — most of it can wait. The relief is in the sorting. 🔴 Truly urgent: register the death where required, secure the home/pets/dependents, anything time-boxed by law or safety. 🟡 Soon: employer, main bank, landlord/ mortgage, benefits that must be stopped or claimed. 🟢 Whenever: subscriptions, memberships, social accounts, sentimental admin — months, no rush, and saying so is the point.
- Script the "they died" call once. The repeated disclosure is a specific cruelty. Provide the short, calm template ("I'm calling to report a death and close/settle an account — the person is [name], date of death [date]") plus what they'll typically ask for (death certificate copies, account details), so each call is a form to fill, not a fresh wound.
- Build the list from THIS life. Generic checklists miss the person's actual footprint. Reconstruct it: income sources, the direct debits, the phone/energy/ water, the digital accounts (email is the master key — see [[digital-death-plan]]), the memberships, the pet, the plants. Order-of-notification matters (some accounts need others closed first); the sequence handles it.
- Permission to go slow and delegate. The most useful sentence in the whole skill: almost nothing here is as urgent as it feels, and the 🟢 pile can wait until you can face it. Name what can be delegated (a friend can make cancellation calls with a letter of authority), what can be paused, and that leaving things undone for a while is normal, not negligent.
- Hand off the professional parts cleanly. Probate/estate administration, tax, and benefits are real processes with real rules that vary by place — the skill names them, flags "get proper advice / use the official service," and does NOT improvise law. It gets you organized enough to make those conversations short.
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.
- 10d ago First seen · 122 lines · 130 tokens per session scan A 7dea7b36fd8e
grief-admin is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,352 stars, last pushed 2d ago), licensed MIT. It adds 130 tokens to every session and 1,554 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.
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.