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/salary-benchmarking)<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/salary-benchmarking"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/salary-benchmarking/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/salary-benchmarking"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/salary-benchmarking.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 | $0.00141 | $0.01109 |
| Opus 5 | $0.00071 | $0.00554 |
| Sonnet 5 | $0.00028 | $0.00222 |
| Haiku 4.5 | $0.00014 | $0.00111 |
Grade A, and why
salary-benchmarking 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Salary Benchmarking
"Am I underpaid?" and "what should I ask for?" both need the same thing: a defensible number, not a guess or a single glassdoor figure. This builds that range by triangulating sources and adjusting for the factors that actually move pay — level, location, industry, skills, company size — then places you within the band and helps you frame it. (Making the ask itself is a separate negotiation skill.)
What This Skill Produces
- A research method — how to build a range from multiple sources (surveys, aggregators, postings, peers, recruiters) rather than one figure
- The adjusting factors — how level/seniority, location/cost-of-living, industry, in-demand skills, and company size/stage shift the number
- Your position in the band — a reasoned estimate of where you likely sit (and why), given your experience and value
- A defensible range — a low/target/high you can justify with the factors behind it
- Framing guidance — how to state the number and the evidence, without overclaiming
- A triangulation caveat — pay data is noisy and often stale; cross-check, and adjust for your specifics
Required Inputs
Ask for these if not provided:
- The role — title, level/seniority, and field
- Location — and whether the role is remote (which market applies)
- Your profile — years, key/in-demand skills, notable results
- Context — current pay, company size/industry, and the goal (raise, offer, new role)
- Sources seen — any numbers you already have
Framework: Triangulate, Adjust, Position
- Use multiple sources. No single site is truth — combine salary surveys, aggregators, live job postings, peer/recruiter input, and community data to form a range.
- Adjust for the real drivers. Level, location/cost-of-living, industry, scarce skills, and company size/stage can each shift pay substantially — apply them to the raw range.
- Place yourself honestly. Position within the band based on your actual experience, skills, and results — not aspiration or imposter-driven lowballing.
- Build a defensible range. Produce a low/target/high with the reasoning, so the number survives scrutiny.
- Frame with evidence, not entitlement. Present the number tied to market data and your value; avoid a single cherry-picked figure or an unbacked demand.
- Caveat the data. It's noisy and can lag the market — triangulate and adjust rather than trusting one source or a stale number.
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 · 71 lines · 141 tokens per session scan A 22f4c118c8d2
salary-benchmarking is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,352 stars, last pushed 3d ago), licensed MIT. It adds 141 tokens to every session and 1,109 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 2026-09-03.
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.