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/roi-estimatorWrote 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/roi-estimator)<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/roi-estimator"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/roi-estimator/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/roi-estimator"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/roi-estimator.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 | $0.00086 | $0.00803 |
| Opus 5 | $0.00043 | $0.00402 |
| Sonnet 5 | $0.00017 | $0.00161 |
| Haiku 4.5 | $0.00009 | $0.00080 |
Grade A, and why
roi-estimator 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ROI Estimator Skill
Every "should we spend on this?" decision needs a defensible number. This skill estimates the return — ROI %, payback period, and a simple NPV that accounts for the time value of money — from costs and expected benefits, with the assumptions stated and a sensitivity check, so a business case survives the first sceptical question instead of collapsing.
Required Inputs
Ask for these only if they aren't already provided:
- Costs — upfront cost, and any ongoing/recurring cost (per period).
- Benefits — the expected gain per period (revenue uplift, cost saved, time saved × loaded rate). Quantify; if it's an estimate, say so.
- Time horizon — over how many periods to evaluate (e.g. 3 years).
- Discount rate — for NPV (default ~10%); state it.
Output Format
ROI: [investment]
1. The numbers (via the helper):
| Metric | Value |
|---|---|
| Total cost (over horizon) | |
| Total benefit (over horizon) | |
| Net benefit | |
| ROI % | |
| Payback period | |
| Simple NPV (@ discount rate) |
2. The verdict — worth it / marginal / no, in one line, and against what bar (e.g. beats the discount-rate hurdle, payback within tolerance).
3. Assumptions — list them explicitly. The benefit is usually the soft number — flag it, and give a conservative / expected / optimistic range rather than a single point.
4. Sensitivity — the one assumption the conclusion hinges on, and at what value the decision flips.
Programmatic Helper
scripts/roi.py (stdlib only) computes ROI, payback, and NPV:
# in.json: {"upfront_cost":50000,"recurring_cost":2000,"benefit_per_period":18000,"periods":36,"discount_rate_annual":0.1,"period":"month"}
python3 scripts/roi.py in.json
python3 scripts/roi.py in.json --json
Quality Checks
- Costs include recurring/ongoing, not just upfront
- NPV is computed (time value of money), not just raw ROI
- Benefits are given as a range (conservative/expected/optimistic), not a single optimistic point
- Every assumption is listed explicitly
- A sensitivity note names the assumption the verdict hinges on and its flip point
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 · 73 lines · 86 tokens per session scan A 1ba03ccc6a79
roi-estimator is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,352 stars, last pushed 4d ago), licensed MIT. It adds 86 tokens to every session and 803 once invoked, about $0.0004 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.