collections-email

collections-email is a cursor rule for Cursor from mohitagw15856/pm-claude-skills. It costs 81 tokens per session (929 once invoked), scanned A, original, MIT.

A set of polite but increasingly firm emails for collecting overdue invoice payments. It starts with a friendly reminder and progresses toward a final notice while leaving payment details easy to find.

In plain words
What is it for?
Writing payment reminders, dunning sequences, and final notices with invoice details, deadlines, payment links, and reviewed escalation language.
Why use it?
Late-payment messages are often sent too late or become unnecessarily harsh. A staged sequence gives the sender a consistent way to follow up while considering the business relationship and local rules.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc). Also seen: positional $N argument.

Good fit Writing payment reminders, dunning sequences, and final notices with invoice details, deadlines, payment links, and reviewed escalation language.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/mohitagw15856/pm-claude-skills/collections-email
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 · 1,352 stars · on GitHub · mohitagw15856.github.io

Install

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.

Clone the repo
git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills

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 collections-email

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

Your own site · 80×15
<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/collections-email"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/collections-email.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 929 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 $0.00081 $0.00929
Opus 5 $0.00041 $0.00464
Sonnet 5 $0.00016 $0.00186
Haiku 4.5 $0.00008 $0.00093

Measured 8d ago against content hash b321aef8ad62, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

collections-email 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.

exports/cursor/pm-accounting/collections-email/collections-email.mdc · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Collections Email Skill

Chasing payment is uncomfortable, so it's often done too late or too harshly. The effective approach is a staged sequence that starts friendly and firms up on a schedule — always professional, always making it trivially easy to pay. This skill writes that sequence so you get paid without burning the relationship.

Note: this is a communication aid, not legal or debt-collection advice. Late-payment interest, statutory rights, and regulated debt-collection rules vary by jurisdiction — confirm any interest/late fees and escalation (collections agency, legal) with an accountant/lawyer before acting on them.

Working from a brief

Given "chase a client whose $5,000 invoice is 2 weeks overdue", write the full sequence anyway — infer a sensible cadence and tone progression, marking specifics (insert invoice #, amount, dates, payment link). Don't state late-fee/interest amounts as enforceable — flag them to confirm. Never threaten beyond what's lawful/intended.

Required Inputs

Ask for these only if they aren't already provided (else mark to insert):

  • The invoice — number, amount, original due date, and how overdue it is.
  • The relationship — client name, contact, and whether they're a valued ongoing client or a one-off.
  • Terms — your payment terms and any agreed late-fee/interest (flag to confirm enforceability).
  • Payment method — exactly how they can pay (link, bank details), to remove friction.

Output Format

Collections Sequence: [invoice]

A staged set of emails, each short, professional, and with a clear pay-now path:

  1. Pre-due reminder (optional, ~3–5 days before) — friendly heads-up the invoice is due soon.
  2. Due-date / just-overdue (day 0–3) — assume an oversight; warm nudge, restate amount + due date + how to pay.
  3. Overdue reminder (~7–14 days) — firmer, still polite; note it's now overdue, ask for a payment date or to flag an issue.
  4. Second overdue (~21–30 days) — clear and direct; reference the terms, request immediate payment or a call, mention any agreed late fee (confirm).
  5. Final notice (~30–45 days) — formal; state the next step if unpaid (pause work, escalate per terms) — factual, not threatening.

Read the full file on GitHub · 68 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. 8d ago First seen · 68 lines · 81 tokens per session scan A b321aef8ad62

Subscribe to this mod's changes

collections-email is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,352 stars, last pushed 3d ago), licensed MIT. It adds 81 tokens to every session and 929 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.