capital-allocation

capital-allocation is a cursor rule for Cursor from mohitagw15856/pm-claude-skills. It costs 82 tokens per session (878 once invoked), scanned A, original, MIT.

A plan for dividing a fixed budget or number of employees among competing initiatives. It compares expected return, strategic fit, required funding, and constraints before showing what gets funded and where the cut-off falls.

In plain words
What is it for?
Use it to allocate money or headcount, build an investment portfolio across projects, and decide which initiatives must be funded or stopped.
Why use it?
When there are more worthwhile projects than available resources, informal decisions can favour the loudest request. A scored portfolio makes the trade-offs and rejected work explicit.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc).

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/capital_allocate.py items.json --budget 1000.

Good fit Use it to allocate money or headcount, build an investment portfolio across projects, and decide which initiatives must be funded or stopped.

Compare 6 cursor rules from other repositories ↓
About the project

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.

mohitagw15856/pm-claude-skills · 1,357 stars · on GitHub · mohitagw15856.github.io

Install

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.

Clone the repo
git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills
agentmods
npx agentmods add rules/mohitagw15856/pm-claude-skills/capital-allocation

Made for: Cursor.

Wrote 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.

agentmods badge for capital-allocation

README.md
[![agentmods](https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/capital-allocation/github.svg)](https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/capital-allocation)
Your own site
<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/capital-allocation"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/capital-allocation/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.

agentmods 80×15 button for capital-allocation

Your own site · 80×15
<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/capital-allocation"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/capital-allocation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 82 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 878 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00082 $0.00878
Opus 5 $0.00041 $0.00439
Sonnet 5 $0.00016 $0.00176
Haiku 4.5 $0.00008 $0.00088

Measured 9d ago against content hash aa9146cd835a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

capital-allocation 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 9d 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.

exports/cursor/pm-business/capital-allocation/capital-allocation.mdc · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Capital Allocation Skill

Allocating capital is the core executive job: a fixed pot, more good ideas than money, and the need to say no on the record. This skill scores initiatives by expected return and strategic fit per unit of cost, allocates against the cap (honouring must-funds), and makes the cut line explicit — so funding is a defensible portfolio choice, not the loudest voice in the room.

Required Inputs

Ask for these only if they aren't already provided:

  • The cap — the total budget or headcount to allocate, and the period.
  • The initiatives — each with its cost, expected return (revenue, savings, or a strategic value), and strategic fit.
  • Constraints — anything that must be funded (compliance, keep-the-lights-on) or can't be partially funded.
  • The objective — what you're optimising: near-term return, strategic positioning, or a balance.

Output Format

Capital Allocation: [pot], [period]

1. Objective & cap — what you're optimising and the total available.

2. Scored initiatives — a table; score = expected value × strategic fit, normalised per unit cost:

Initiative Cost Expected return Strategic fit (1–5) Score / $ Must-fund?

3. The allocation — funded vs. unfunded against the cap, with budget utilisation. Must-funds first, then highest score/$ until the cap binds.

4. The cut line — the marginal initiative that just missed, and what it would take to fund it (the most useful number for the debate).

5. Rationale & trade-offs — why the portfolio is balanced this way, what's deliberately not funded, and the reversibility of each bet.

6. Re-evaluation triggers — what would change the allocation mid-period (a bet pays off early, a must-fund grows).

Programmatic Helper

scripts/capital_allocate.py (stdlib only) does the allocation deterministically — must-funds first, then by score-per-cost until the cap binds — and reports the cut line:

# items.json: [{"name":"Mobile revamp","cost":300,"expected_return":900,"strategic_fit":5,"must_fund":false}, ...]
python3 scripts/capital_allocate.py items.json --budget 1000
python3 scripts/capital_allocate.py items.json --budget 1000 --json

Read the full file on GitHub · 72 lines

Changes

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.

  1. 9d ago First seen · 72 lines · 82 tokens per session scan A aa9146cd835a

Subscribe to this mod's changes

capital-allocation is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,357 stars, last pushed today), licensed MIT. It adds 82 tokens to every session and 878 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.