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.
npx agentmods add rules/adadiamonds/agent-tools/cursorrulesgit clone --depth 1 https://github.com/adadiamonds/agent-toolsWhat 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 | $0.00446 | $0.00446 |
| Opus 5 | $0.00223 | $0.00223 |
| Sonnet 5 | $0.00089 | $0.00089 |
| Haiku 4.5 | $0.00045 | $0.00045 |
Grade B, and why
cursorrules scanned grade B with 1 finding 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.
Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
- mcp.json servers need a type and an absolute https url; no secrets in headers. What it actually says
Cursor rules for adadiamonds/agent-tools
This repository is the official public Ada Diamonds plugin for AI agents: an Agent Plugins 1.0.0 manifest (plugin.json), the MCP server list (mcp.json: https://www.adadiamonds.com/mcp and https://www.adadiamonds.com/mcp/docs), and four Agent Skills under skills/ (ada-diamonds-shopping, ada-diamonds-api, ada-diamonds-mcp, ada-diamonds-commerce). There is no application code.
Source of truth for every fact: https://www.adadiamonds.com/developers (markdown via Accept: text/markdown), https://www.adadiamonds.com/openapi.json, https://www.adadiamonds.com/agents.md. If a skill disagrees with the live docs, fix the skill.
When asked about Ada Diamonds' API, MCP servers, or checkout, read the relevant skills//SKILL.md first and answer from it, not from memory.
Editing rules:
- Never invent endpoints, parameters, scopes, or prices.
- Prices are US dollars as decimals, never cents.
- An engagement ring is a setting plus a loose diamond, priced separately; ring examples show both numbers and the sum.
- SKILL.md frontmatter: name equals the directory name; description non-empty, max 1024 chars, says what the skill does and when to use it; keep license: MIT and metadata.homepage; single-line values only.
- Keep SKILL.md under 500 lines; long tables go in references/ inside the skill and are linked relatively.
- plugin.json may only contain: $schema, name, version, description, author, homepage, repository, license, keywords, extensions. Never declare skills or MCP servers inline in plugin.json.
- mcp.json servers need a type and an absolute https url; no secrets in headers.
- No em dashes in prose; use commas, periods, or parentheses.
- Bump plugin.json version and add a CHANGELOG.md line for user-visible changes.
Validate before committing: node scripts/validate.mjs (exit 0 = valid). CI runs the same script.
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.
- yesterday First seen · 21 lines · 446 tokens per session scan B 31ce90fbf402
cursorrules is a cursor rule published in the GitHub repository adadiamonds/agent-tools (2 stars, last pushed 3d ago), licensed MIT. It adds 446 tokens to every session, about $0.0022 per session on Opus 5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other cursor rules, from other repositories
cursor
You are working on the checkout service. Preserve transaction integrity and auditability.
pro-deck-builder
Create polished HTML slide decks and PDF-ready documents for consulting deliverables. Uses the RRBC design system with warm light mode, dark mode cover pages, Lora/Inter/Roboto Mono typography, and data visualization palette. Trigger on 'deck', 'slides', 'presentation', 'pitch deck', 'keynote', 'report', or 'PDF'.
release-notes
Generate changelog entries and GitHub releases from git history. Categorizes commits into features, fixes, breaking changes, and docs. Supports conventional commits, PR-based grouping, and semantic versioning. Creates formatted CHANGELOG.md entries and GitHub releases.
facebook-ads
Meta Ads (Facebook & Instagram) platform expertise. Audit campaigns, audiences, creative strategy, pixel tracking, and CAPI. Use when the user asks about Facebook Ads, Instagram Ads, Meta Ads, social media advertising, Advantage+ campaigns, or Meta pixel/CAPI setup.
paddle-integration
Conventions for Paddle integration code.
faststore-faststore-storefront-ref-project-structure-routes-and-config
FastStore project structure, routes, CLI build pipeline, store configuration (discovery.config.js), and naming conventions. Use when understanding how a FastStore project is organized, how the @faststore/cli works, what files to create or modify, how routing works, or how to configure store settings like SEO, API…