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/make-friends-as-an-adult)<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/make-friends-as-an-adult"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/make-friends-as-an-adult/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/make-friends-as-an-adult"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/make-friends-as-an-adult.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 | $0.00128 | $0.01068 |
| Opus 5 | $0.00064 | $0.00534 |
| Sonnet 5 | $0.00026 | $0.00214 |
| Haiku 4.5 | $0.00013 | $0.00107 |
Grade A, and why
make-friends-as-an-adult 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 13d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Make Friends as an Adult
Friendship happened automatically as a kid — forced proximity and endless repeated contact. As an adult, that scaffolding disappears, so friends have to be built on purpose, which feels awkward and vulnerable and stops most people. This gives a real plan: where to find people you'd genuinely click with, the specific moves that turn a friendly acquaintance into an actual friend, and permission for it to feel a bit awkward — because it does for everyone.
What This Skill Produces
- Where to meet the right people — settings that combine shared interest and repeated exposure (the two ingredients of friendship), tuned to you
- The acquaintance→friend move — the specific actions that convert (initiating plans, consistency/repetition, and a little vulnerability) — most people stall at acquaintance
- A low-pressure action plan — small, doable steps (join the thing, follow up, invite once) that don't require being an extrovert
- The mindset reframe — that the awkwardness and fear of rejection are normal and shared, and that most people also want more friends
- A follow-through habit — the "actually text them" nudge, since intentions don't build friendships
Required Inputs
Ask for these if not provided:
- Your situation — new to an area, life changed (moved, had kids, left a job), or just drifted
- Your interests — the shared-activity hooks to meet people around
- Your temperament — introvert/extrovert and social energy
- What's stopping you — awkwardness, time, not knowing where, past rejection
Framework: Proximity + Repetition + Initiative
- Find shared-interest + repeated-exposure settings. Friendships form where you see the same people repeatedly around something you both care about — classes, clubs, teams, volunteering, regular events. Target those, not one-off mixers.
- Initiate — don't wait. Adults rarely get "adopted" into friend groups; you have to make the first move (suggest a coffee, invite to a thing). Waiting is why people stay lonely.
- Repeat. Friendship needs multiple contacts — one nice chat isn't a friend. Build in consistency (the regular class, the repeated invite).
- Add a little vulnerability. Sharing something real (beyond small talk) is what deepens acquaintance into friendship — go slightly past surface.
- Normalize the awkward. The fear of seeming needy or being rejected is universal; most people also want more friends and will be glad you reached out.
- Follow through. The plan fails on the "I'll text them sometime" step — make the follow-up concrete.
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.
- 13d ago First seen · 68 lines · 128 tokens per session scan A bd2bfd1b81d7
make-friends-as-an-adult is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,357 stars, last pushed yesterday), licensed MIT. It adds 128 tokens to every session and 1,068 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.