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/clone-brief)<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/clone-brief"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/clone-brief/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/clone-brief"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/clone-brief.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 | $0.00098 | $0.01253 |
| Opus 5 | $0.00049 | $0.00626 |
| Sonnet 5 | $0.00020 | $0.00251 |
| Haiku 4.5 | $0.00010 | $0.00125 |
Grade A, and why
clone-brief 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 11d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clone Brief Skill
"Sorry, can't make it — can you represent me?" usually transmits a vibe and a prayer. Then your representative gets asked the one question you didn't cover, guesses, and you spend Thursday unwinding it. A clone brief is what should have gone instead of you: your positions with their reasoning, your fallbacks in order, the red lines that end the conversation, what you'd happily trade — and the explicit boundary of what your representative may agree to versus must bring back. One page, readable in two minutes by a colleague, and structured enough that an agent could carry it too. In a world of A2A meetings, this is the artifact that attends.
What This Skill Produces
- The clone brief: context in three lines, then stances / fallbacks / red lines / tradables / delegation boundary, each with the why attached
- A 60-second verbal version for briefing the carrier in the corridor
- A question-anticipation table: the questions likely to come up, with your answers — including the honest "I haven't decided; here's my leaning"
- A debrief ask: the 3 things you want reported back
Required Inputs
Ask for (if not already provided):
- The meeting: decision at stake, who's in the room, what they each want (as far as known)
- Your position and — this is the load-bearing part — why; the reasoning is what lets a representative handle the unanticipated
- What you'd accept as fallback, what's tradable, what's a walk-away
- Who carries the brief (peer? report? someone from another team? an agent?) and how much you trust their judgment on this topic
Process
- Compress context ruthlessly. Three lines: what's being decided, why it matters to you, where the tension is. The carrier has two minutes; history lessons stay home.
- Ladder the positions. For each issue at stake: IDEAL (open with this) → ACCEPTABLE (agree without checking) → BRING BACK (don't agree; capture and return) → RED LINE (say no in the room, with the scripted sentence to say). Attach one-line reasoning to each rung — reasoning is what travels; conclusions alone can't handle follow-ups.
- Name the tradables. What you'd concede happily and what you want in exchange — a representative who knows your currency can negotiate; one who only knows your demands can only repeat them.
- Draw the delegation boundary explicitly. The sentence that prevents the Thursday unwind: "You may commit up to X; beyond that, 'I'll take it back to [name] by [time]' — that sentence is always a win, never a failure."
- Anticipate the questions. The 3–6 things the room will ask, answered. Where you're genuinely undecided, say so with your leaning — a representative bluffing certainty in your name is worse than one honestly deferring.
- Script the debrief. Three asks: what was decided · what was said about [the thing you care about] · what surprised you. Anything more won't be remembered.
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.
- 11d ago First seen · 110 lines · 98 tokens per session scan A 68947ef31b15
clone-brief is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,352 stars, last pushed 2d ago), licensed MIT. It adds 98 tokens to every session and 1,253 once invoked, about $0.0005 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.