pro-report-builder

pro-report-builder is a cursor rule for Cursor from thatrebeccarae/claude-marketing. It costs 97 tokens per session (3,802 once invoked), scanned A, original, MIT.

A set of templates and instructions for creating polished technical reports as standalone HTML documents, with portrait pages and reusable report elements. The documents can be converted to PDF using Chrome in headless mode, meaning without opening a visible browser window.

In plain words
What is it for?
Use it for audit reports, assessments, technical briefs, case studies, data tables, KPI summaries, and other consulting documents.
Why use it?
It removes the need to design report layouts and styles from scratch. It also gives a consistent way to organize multi-page written deliverables.

Cursor rule for Cursor

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

Good fit Use it for audit reports, assessments, technical briefs, case studies, data tables, KPI summaries, and other consulting documents.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/thatrebeccarae/claude-marketing/pro-report-builder
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/thatrebeccarae/claude-marketing

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 pro-report-builder

README.md
[![agentmods](https://agentmods.dev/badge/rules/thatrebeccarae/claude-marketing/pro-report-builder.svg)](https://agentmods.dev/rules/thatrebeccarae/claude-marketing/pro-report-builder)
Your own site
<a href="https://agentmods.dev/rules/thatrebeccarae/claude-marketing/pro-report-builder"><img src="https://agentmods.dev/badge/rules/thatrebeccarae/claude-marketing/pro-report-builder.svg" alt="Measured on agentmods" height="20"></a>
Per session 97 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,802 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 $0.00097 $0.03802
Opus 5 $0.00048 $0.01901
Sonnet 5 $0.00019 $0.00760
Haiku 4.5 $0.00010 $0.00380

Measured 8d ago against content hash c777ffdd0137, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

pro-report-builder 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.

integrations/cursor/pro-report-builder.mdc · 351 lines

How it starts

The opening of the file, as written. The whole thing — 351 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pro Report Builder

Polished consulting reports as standalone HTML. Export to PDF via Chrome headless.

Quick Reference

Task Approach
Create report from scratch Read REFERENCE.md for CSS + HTML patterns
Add a new component type Compose from existing components in REFERENCE.md
Export to PDF Chrome headless --print-to-pdf (see Export section)
Customize brand tokens Edit CSS custom properties in :root block

When to Use This Skill vs pro-deck-builder

pro-report-builder pro-deck-builder
Format 8.5x11" portrait pages 16:9 landscape slides
Content flow Multi-page, flowing text Single-slide compositions
Export Chrome headless --print-to-pdf Puppeteer
Use for Audit reports, assessments, written deliverables Presentation decks, pitch slides

Before You Start

Step 1: Understand the Brief

Ask the user:

  1. What type of document? Audit report, assessment, technical brief, case study?
  2. How many pages roughly? Helps plan section flow and page distribution.
  3. What data do they have? Raw numbers, API exports, spreadsheets? Pull exact values -- never estimate when actuals exist.
  4. Where should the file be saved? Default: ./output/

Step 2: Plan the Document Structure

Every report follows this structure:

Cover Page --> Executive Summary --> Analysis Sections (3-6) --> Prioritized Recommendations --> Quick Wins --> Appendix

Each analysis section should occupy 1-2 pages. Recommendation cards are the most space-intensive component -- budget carefully.

Design System

Customizable Brand Identity

The included design system provides a professional default. All color tokens, typography, and spacing are defined as CSS custom properties in :root. Override these to match your brand.

Color Tokens

:root {
  /* Accent -- change this to your brand color */
  --accent:        #3D7A5C;
  --accent-dim:    rgba(61, 122, 92, 0.08);
  --accent-dark:   #2E6B4A;
  --accent-light:  #6AB88A;

  /* Severity */
  --excellent:     #2e8b57;
  --warning:       #D97706;
  --critical:      #c0392b;

  /* Light-mode backgrounds (warm cream) */
  --bg-page:       #FAF7F2;
  --bg-surface:    #F2EDE6;
  --bg-elevated:   #EBE5DD;

  /* Light-mode text */
  --text-primary:  #0f0e0e;
  --text-body:     #57606a;
  --text-muted:    #8b949e;

  /* Borders */
  --border:        rgba(15, 14, 14, 0.1);
  --border-dim:    rgba(15, 14, 14, 0.06);

  /* Callout tints */
  --tint-blue:     #eaf2ed;
  --tint-green:    #eaf5ef;
  --tint-red:      #fef2f2;
  --tint-amber:    #fffbeb;

  /* Dark mode (cover page only) */
  --dark-bg:       #141414;
  --dark-surface:  #1E1E1E;
  --dark-text:     #f0f3f6;
  --dark-muted:    #6e7681;
  --dark-secondary:#9ca3af;
  --dark-border:   rgba(255, 255, 255, 0.08);
}

Read the full file on GitHub · 351 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 · 351 lines · 97 tokens per session scan A c777ffdd0137

Subscribe to this mod's changes

pro-report-builder is a cursor rule published in the GitHub repository thatrebeccarae/claude-marketing (132 stars, last pushed 3mo ago), licensed MIT. It adds 97 tokens to every session and 3,802 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 2026-08-30.