cursorrules

A set of project rules for PitchDocs, a Claude Code plugin that creates repository documentation in Markdown. It describes the project structure, writing standards, and optional checks.

In plain words
What is it for?
Use it when working on PitchDocs documentation, its skills, agents, commands, rules, or content checks. It also helps keep changes aligned with the project's Australian English and documentation standards.
Why use it?
It gives the coding agent consistent guidance about how this documentation project is organised and written. This reduces guesswork when updating or reviewing the files.

Cursor rule for Cursor

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.

agentmods
npx agentmods add rules/littlebearapps/pitchdocs/cursorrules
Clone the repo
git clone --depth 1 https://github.com/littlebearapps/pitchdocs

Made for: Cursor.

Per session 642 This file is loaded in full into every session.
When invoked 642 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00642 $0.00642
Opus 5 $0.00321 $0.00321
Sonnet 5 $0.00128 $0.00128
Haiku 4.5 $0.00064 $0.00064

Measured yesterday against content hash fcd13e8bfcbc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursorrules 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 yesterday.

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.

.cursorrules · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PitchDocs — Cursor Rules

You are working on PitchDocs, a Claude Code plugin that generates marketing-quality repository documentation. This is a pure Markdown project with no code runtime.

Architecture

  • Skills (16): .claude/skills/*/SKILL.md — reference knowledge loaded on-demand
  • Agents (4): .claude/agents/*.md — docs-writer (orchestrator), docs-researcher, docs-reviewer; agents/docs-freshness.md — installed per-project by /pitchdocs:activate
  • Rules (3 auto-loaded + 2 installable): .claude/rules/content-filter.md (global); .claude/rules/doc-standards.md, .claude/rules/docs-awareness.md (installed auto-loaded); rules/doc-standards.md, rules/docs-awareness.md (source templates installed per-project by /pitchdocs:activate)
  • Commands (16): commands/*.md — 14 active + 2 stubs redirecting to ContextDocs
  • Hooks (1 opt-in): hooks/content-filter-guard.sh — installed per-project by /pitchdocs:activate install strict (Claude Code only)

Writing Standards

  • Australian English (realise, colour, behaviour, licence/license)
  • Benefit-driven language: [Feature] so you can [outcome] — [evidence] (with optional JTBD job mapping for richer benefits)
  • 4-question test on every doc: problem solved? usable? credible? linked?
  • Progressive disclosure: non-technical first, technical deeper
  • Every feature claim must trace to actual code (file path, function, config)

File Sync Requirements

When adding skills or commands, update all of:

  • README.md (commands table, features section)
  • AGENTS.md (skills table, commands table, if applicable)
  • llms.txt (file reference with benefit description)
  • .github/ISSUE_TEMPLATE/bug_report.yml (component dropdown)

Protected Files

docs/faq/index.md is load-bearing — it sources the marketing-site FAQPage JSON-LD on https://littlebearapps.com/help/pitchdocs/. The docs-sync pipeline (scripts/docs-sync.config.ts in littlebearapps/littlebearapps.com, mapped under pitchdocs with category: faq) hard-fails if the directory is missing. Keep ≥7 question-shaped H2 headings (##); edit entries in place; never delete. See Protected Documentation Files in AGENTS.md.

Read the full file on GitHub · 40 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. yesterday First seen · 40 lines · 642 tokens per session scan A fcd13e8bfcbc

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository littlebearapps/pitchdocs (7 stars, last pushed 3mo ago), licensed MIT. It adds 642 tokens to every session, about $0.0032 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 2026-08-31.