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/boundary-setting-scripts)<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/boundary-setting-scripts"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/boundary-setting-scripts/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/boundary-setting-scripts"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/boundary-setting-scripts.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 | $0.00131 | $0.01081 |
| Opus 5 | $0.00066 | $0.00541 |
| Sonnet 5 | $0.00026 | $0.00216 |
| Haiku 4.5 | $0.00013 | $0.00108 |
Grade A, and why
boundary-setting-scripts 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Boundary-Setting Scripts
A boundary is only real if you can say it out loud and hold it — which is exactly what most people can't do, so they hint, resent, and explode instead. This helps you name the boundary you actually need, gives you warm-but-firm words to state it (no over-explaining, no apologizing it into nothing), and prepares you for the pushback — because the guilt-trip and the "you're being difficult" are coming, and folding at them means you never had a boundary.
What This Skill Produces
- The boundary, clarified — what you actually need to change, stated as a clear limit (not a vague wish)
- A warm-but-firm script — the words to say it kindly and directly, without over-justifying or apologizing it away
- The hold-the-line plan — responses to the pushback, guilt-trips, and "you've changed / you're overreacting"
- The consequence — what you'll do if the boundary isn't respected (a boundary with no follow-through is a suggestion)
- A relationship-aware tone — calibrated to who it's with (a boss ≠ a partner ≠ a parent)
Required Inputs
Ask for these if not provided:
- The situation — who, and what they're doing that you need to change
- What you need — the specific limit (time, behavior, topic, availability)
- The relationship — friend, family, partner, coworker, boss (changes tone and leverage)
- The dynamic — how they usually react, and whether you've raised it before
- Your goal — change the behavior while keeping the relationship, or a firmer stance
Framework: Name It, State It, Hold It
- Clarify the actual boundary. Turn a vague frustration into a specific limit — "I need X to stop" or "I'm not available for Y" — because you can't state what you haven't defined.
- State it warm and firm. Lead with care if the relationship warrants, then the boundary plainly — and stop. Over-explaining and apologizing invite negotiation.
- Don't justify it to death. "No" is a complete sentence; a boundary doesn't require a defense that gives them something to argue with.
- Prepare for pushback. Guilt, anger, and "you're being unreasonable" are common — a calm broken-record restatement holds the line without a fight.
- Attach a consequence. Decide what you'll actually do if it's ignored (leave the conversation, reduce contact, escalate) — and be prepared to follow through, or it's not a boundary.
- Calibrate to the relationship. The words for a boss differ from a parent from a partner — tune tone and firmness accordingly.
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 · 68 lines · 131 tokens per session scan A f97ed51dfe12
boundary-setting-scripts is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,345 stars, last pushed yesterday), licensed MIT. It adds 131 tokens to every session and 1,081 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 2026-08-30.
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-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.