agentmods.dev

04-ronyup

04-ronyup is a cursor rule for Cursor from clubpay/ronykit. It costs 0 tokens per session (580 once invoked), scanned A, original, BSD-3-Clause.

Project rules for ronyup, a tool that scaffolds applications and provides an MCP server with development knowledge and tools.

In plain words
What is it for?
Use them when maintaining ronyup, its generated app structure, MCP resources, bundled skills, or design gates.
Why use it?
They show where to change scaffolding behavior, knowledge, prompts, skills, and enforcement checks.

Cursor rule for Cursor

not rated 38 3d ago A scan 0 tokens original BSD-3-Clause
View the source file clubpay/ronykit
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/clubpay/ronykit/04-ronyup
Clone the repo
git clone --depth 1 https://github.com/clubpay/ronykit

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 04-ronyup

README.md
[![agentmods](https://agentmods.dev/badge/rules/clubpay/ronykit/04-ronyup.svg)](https://agentmods.dev/rules/clubpay/ronykit/04-ronyup)
Your own site
<a href="https://agentmods.dev/rules/clubpay/ronykit/04-ronyup"><img src="https://agentmods.dev/badge/rules/clubpay/ronykit/04-ronyup.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 580 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.00580
Opus 5 $0.00000 $0.00290
Sonnet 5 $0.00000 $0.00116
Haiku 4.5 $0.00000 $0.00058

Measured 4d ago against content hash 11b379e97c25, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

04-ronyup 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 4d 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.

.cursor/rules/04-ronyup.mdc · 24 lines

What it actually says

ronyup (scaffolder + MCP server)

ronyup/ produces scaffolded app workspaces and serves the ronyup mcp knowledge/tools that drive agents. When changing how agents build apps, edit these — not AGENTS.md.

  • MCP knowledge lives in ronyup/cmd/mcp/knowledge/ and is embedded + auto-loaded by loader.go (no registration needed — dropping a .md file is enough):
    • server/instructions.md — always injected on MCP connect (the portable, cross-agent backbone).
    • resources/{architecture,packages,characteristics,tools}/*.md — read on demand (knowledge://ronyup/<category>/<name>).
    • prompts/*.md — workflow prompts (e.g. design-new-service, design-frontend).
  • Bundled skills live in ronyup/internal/skeleton/skills/<id>/SKILL.md and must be registered in skillCatalog (ronyup/internal/scaffold/skills.go); authoring heuristic (single file vs. rules/ tree) is in internal/skeleton/skills/README.md. copySkills ships the whole directory.
  • Enforcement is gates and hooks, not prose (small models ignore advisory text):
    • ronyup/cmd/mcp/tools/scaffold/gate.go — the SRS/SDD design gate that scaffold_feature enforces (portable across MCP clients).
    • ronyup/internal/skeleton/backend/verify.sh and internal/skeleton/frontend/verify.sh — the make verify quality gates (test coverage, design-doc, lint/build/stories).
    • ronyup/internal/skeleton/workspace/.cursor/hooks/*.sh + hooks.jsontmpl — Cursor stop hooks that auto-loop the agent until a gate passes.
  • Keep the layers consistent. A behavior change usually touches several surfaces at once: server/instructions.md, the relevant resources//prompts/ doc, AGENTS.mdtmpl, the ronykit-framework skill (both .agents/skills/.../SKILL.md and the skeleton copy under ronyup/internal/skeleton/workspace/.agents/skills/), and references/mcp-map.md.
  • Verify with cd ronyup && go test ./... (the scaffold integration tests assert the generated gate/hook files exist).

Deep reference: docs/ronyup-guide.md (user-facing CLI and MCP guide).

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. 4d ago First seen · 24 lines · 0 tokens per session scan A 11b379e97c25

Subscribe to this mod's changes

04-ronyup is a cursor rule published in the GitHub repository clubpay/ronykit (38 stars, last pushed 3d ago), licensed BSD-3-Clause. It costs nothing until one of its globs matches a file; then it loads 580 tokens. 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.

Goperformantrest-apirouterrpcrpc-framework
Related

Other cursor rules, from other repositories

agentic-loop

Follow this loop on every development task in this repository. For full conventions, architecture, and examples, see @.github/copilot-instructions.md (source of truth). This rule distills the workflow; do not duplicate that document.

prest/prest · 2,025 tokens

adapter-features

Database-specific features must be implemented in the specialized adapter only. Base adapters (postgres, mysql, etc.) must remain database-agnostic.

prest/prest · 773 tokens

git-commits

Git commit safety — commits are human-only; AI suggests, never executes.

prest/prest · 963 tokens

unit-tests-tdd

TDD required for behavior changes; ≥80% package coverage on touched packages; unit-test conventions.

prest/prest · 375 tokens

adapter-unit-tests

Postgres adapter unit tests are sqlmock-only; no real DB or sqlx.Connect.

prest/prest · 0 tokens

studio-build

After Studio changes, regenerate embedded assets with make studio-build and keep dist in the diff.

prest/prest · 0 tokens