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
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skillsnpx agentmods add rules/mohitagw15856/pm-claude-skills/raise-vs-jumpWrote 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/raise-vs-jump)<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/raise-vs-jump"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/raise-vs-jump/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/raise-vs-jump"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/raise-vs-jump.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 | $0.00100 | $0.01116 |
| Opus 5 | $0.00050 | $0.00558 |
| Sonnet 5 | $0.00020 | $0.00223 |
| Haiku 4.5 | $0.00010 | $0.00112 |
Grade A, and why
raise-vs-jump 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Raise vs Jump Skill
"Job hoppers earn more" is true on salary and incomplete on everything else: equity that vests on a cliff you keep resetting, the promotion you were two quarters from, the months of search time, the reputation cost of a short-stint résumé. This skill runs the salary math properly — trajectories, not single offers — and then insists on the checklist of what the salary math can't see, because that checklist decides more of these choices than the compounding does.
What This Skill Produces
- The trajectory table — year-by-year salary and cumulative earnings for both paths
- The crossover year — when cumulative jump-earnings pass cumulative stay-earnings
- The gap at horizon — final salary gap and cumulative gap, on stated assumptions
- The not-in-the-model checklist — scored for this user's actual situation
Required Inputs
Ask for these if not provided:
- Current salary and realistic stay-raise % — their employer's actual recent raises, not the poster in the break room (default 3%, labeled)
- Jump assumptions — bump per jump (default 15%), years between jumps (default 3), raises between jumps (default 2% — jumpers often land at the top of a band and stall)
- The invisible items — unvested equity and its schedule, pension/tenure benefits, promotion proximity, how they'd handle a search
Programmatic Helper
python3 scripts/raise_vs_jump.py --salary 120000
python3 scripts/raise_vs_jump.py --salary 120000 --stay-raise 3.5 --jump-bump 18 --jump-every 3 --json
Deterministic. Models salary only — the script prints its own not-modeled list, and the skill's job is to make that list concrete for the user.
Framework: What the Salary Math Hides
- Vesting resets are the jump tax — walking away from unvested equity and restarting a cliff is often worth more than the bump; compute it in dollars, not vibes
- The stay path has step functions too — a promotion is a 10–20% event; if one is genuinely close (named role, named timeline — not a vague "soon"), model it as a stay-side jump
- Raises between jumps sag — new hires land high in the band and then stall; that's the
--jump-year-raise 2default, and it's why the crossover is later than the first bump suggests - Search risk is asymmetric — a jump that takes 4 months of search or ends in a bad fit erases years of edge; weight it by how in-demand the user actually is
- Three jumps is a pattern — recruiters read tenure; the strategy that maximizes 5-year earnings can shrink 15-year options
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 · 84 lines · 100 tokens per session scan A 4598665c3104
raise-vs-jump is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,352 stars, last pushed 3d ago), licensed MIT. It adds 100 tokens to every session and 1,116 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.