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/site-analysis-report)<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/site-analysis-report"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/site-analysis-report/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/site-analysis-report"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/site-analysis-report.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 | $0.00097 | $0.01358 |
| Opus 5 | $0.00048 | $0.00679 |
| Sonnet 5 | $0.00019 | $0.00272 |
| Haiku 4.5 | $0.00010 | $0.00136 |
Grade A, and why
site-analysis-report 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 8d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Site Analysis Report
Every expensive design change traces back to something about the site that was known but not looked at. Ground conditions, a right of way, a sewer easement, the neighbour's window. This is the systematic sweep before a line is drawn: what is there, what is allowed, what the site can hold, and which unknowns are worth paying to resolve now rather than at foundation stage.
What This Skill Produces
- Physical survey summary — topography, boundaries, existing structures, trees, ground conditions, and services
- A constraints and opportunities read — each constraint with its design consequence, and the aspects worth exploiting
- The statutory and legal position — planning designations, rights of way, easements, covenants, and party wall exposure
- Developable-capacity estimate — what the site could plausibly take, with the assumptions stated
- Orientation and environmental analysis — sun path, prevailing wind, noise sources, flood and drainage
- The risk register — the unknowns, what each could cost, and which are worth investigating before design
Required Inputs
Ask for these if not provided:
- The site — address, boundaries, area, and current use
- What surveys exist — topographical, measured building, arboricultural, ground investigation, drainage, asbestos
- The title information — registered title, easements, covenants, and rights of way if known
- The proposal, if there is one — what the client hopes to build, so capacity can be tested against it
- Local context — planning designations, neighbouring uses, access, and known local sensitivities
Framework: What Is There, What Is Allowed, What It Can Hold
- Separate the physical from the legal. A site can be perfectly buildable and legally constrained, or the reverse. Confusing the two produces schemes that die late.
- Walk the boundaries against the title plan. Fences and titles disagree more often than anyone expects, and the discrepancy is cheapest to find now.
- Find the buried constraints. Sewers, easements, and services crossing the site remove development area without appearing on any drawing.
- Convert every constraint into a design consequence. 'Protected tree' is a note; 'no foundations within 8 m of the northern boundary' is a constraint that shapes the plan.
- Test capacity with stated assumptions. A capacity figure without its assumptions is a number that will be quoted back at you.
- Price the unknowns. For each, what it might cost to be wrong, and what an investigation costs. Some are worth resolving now; say which.
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.
- 8d ago First seen · 91 lines · 97 tokens per session scan A 4b03e0cd4be7
site-analysis-report is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,352 stars, last pushed 3d ago), licensed MIT. It adds 97 tokens to every session and 1,358 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 2026-09-03.
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.