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/architectural-specification)<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/architectural-specification"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/architectural-specification/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/architectural-specification"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/architectural-specification.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 | $0.00101 | $0.01397 |
| Opus 5 | $0.00051 | $0.00698 |
| Sonnet 5 | $0.00020 | $0.00279 |
| Haiku 4.5 | $0.00010 | $0.00140 |
Grade A, and why
architectural-specification 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 7d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architectural Specification Section
Wide tender prices are almost always a specification problem: three contractors read the same section and priced three different buildings. The cure is not more words. It is being precise about performance, unambiguous about who does what at the interfaces, and explicit about what must be submitted and tested — so the cheap tender and the expensive one are pricing the same thing.
What This Skill Produces
- Scope and interfaces — what this section covers, what it does not, and who is responsible at each junction
- Performance requirements — measurable criteria with the standard and test method named
- Product or system definition — either a named product with an equivalence rule, or a performance description a contractor can propose against
- Execution requirements — preparation, sequence, workmanship, and stated tolerances
- Submittals and samples — what must be approved before order, and before installation
- Testing and inspection — what is tested, when, to what standard, and who witnesses
Required Inputs
Ask for these if not provided:
- The element — what is being specified, and where it occurs in the building
- The performance it must achieve — structural, thermal, acoustic, fire, weather, durability, or appearance
- The selection basis — whether a specific product is intended, or a performance outcome is being sought
- The interfaces — what this element meets, and which other trades are involved
- The procurement context — the contract form, the specification system in use, and whether equivalents are permitted
Framework: Performance, Product, Execution, Proof
- Define scope by exclusion as well as inclusion. Most interface defects live in the gap between two sections that each assumed the other covered the junction.
- State performance as a measurable with a test method. 'Weathertight' is not specifiable; a pressure test to a named standard is.
- Choose your specification mode deliberately. Prescriptive names a product and gets what you drew. Performance describes an outcome and transfers design risk. Mixing them accidentally is how you get an unpriceable section.
- If naming a product, state the equivalence rule. What 'or equal approved' means, who approves, what evidence is required, and by when.
- Give tolerances. Unspecified tolerance becomes whatever was achieved, and the argument happens on site with the work already built.
- Specify the proof. Submittals before order, samples before installation, tests during. An unproved requirement is an aspiration.
- Coordinate with the drawings explicitly. Where the two could conflict, say which governs.
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.
- 7d ago First seen · 96 lines · 101 tokens per session scan A 1fda83c19352
architectural-specification is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,352 stars, last pushed 2d ago), licensed MIT. It adds 101 tokens to every session and 1,397 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
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.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.