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/architecture-client-presentation)<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/architecture-client-presentation"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/architecture-client-presentation/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/architecture-client-presentation"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/architecture-client-presentation.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 | $0.00112 | $0.01350 |
| Opus 5 | $0.00056 | $0.00675 |
| Sonnet 5 | $0.00022 | $0.00270 |
| Haiku 4.5 | $0.00011 | $0.00135 |
Grade A, and why
architecture-client-presentation 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 6d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Client Presentation
Clients who reopen decisions usually never made one. They were shown a rendering, said they liked it, and nobody wrote down what had been settled. This structures the meeting so each design move is visibly traceable to the brief they agreed, options carry their real trade-offs, and the session ends with named decisions recorded — which is the only thing that makes a sign-off hold.
What This Skill Produces
- The presentation structure — the order that produces decisions rather than reactions
- Brief-to-design traceability — each major move shown answering something the client asked for
- Options with honest trade-offs — what each costs, gains, and gives up, including the one you do not recommend
- The cost and programme position — where the scheme sits against budget and dates, stated plainly
- The decision request — the specific decisions needed at this meeting, and what is blocked without them
- The decision record — what was agreed, what was rejected, and what remains open, issued afterwards
Required Inputs
Ask for these if not provided:
- The stage and the brief — where the project is, and the agreed brief the design answers
- The design — the scheme and the major moves, with the reasoning behind each
- The options — what genuine alternatives exist, and their cost and programme consequences
- The commercial position — current cost estimate against budget, and the programme status
- The audience — who is in the room, who actually decides, and what each of them cares about
Framework: Brief, Moves, Options, Decision
- Restate the brief first. In their words, from the signed version. Every design decision that follows is then measured against something already agreed rather than against taste.
- Present moves, not views. 'We pushed the mass north to keep the garden in afternoon sun' is a decision the client can engage with. A rendering invites a reaction about the colour of the brick.
- Show the trade-off, always. Every option gives something up. A client who is only shown upside will feel misled when the downside arrives, and will reopen the decision.
- Put cost and programme in the room. Not at the end, not in a covering email. Cost surprises are what destroy trust in a design team.
- Ask for named decisions. 'We need agreement on the roof form today; the structural package is blocked without it.' Vague approval is not a decision.
- Record and issue the same day. Decided, rejected, still open, and what each open item is waiting for. This document is what prevents the reopening.
- Protect the non-negotiables. Where a client request conflicts with statutory or structural reality, say so in the room, once, clearly.
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.
- 6d ago First seen · 95 lines · 112 tokens per session scan A 76eacd9cffee
architecture-client-presentation is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,345 stars, last pushed 2d ago), licensed MIT. It adds 112 tokens to every session and 1,350 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-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
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.