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.
git clone --depth 1 https://github.com/first-fluke/fullstack-starterWrote 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.
[](https://agentmods.dev/rules/first-fluke/fullstack-starter/build-guide)<a href="https://agentmods.dev/rules/first-fluke/fullstack-starter/build-guide"><img src="https://agentmods.dev/badge/rules/first-fluke/fullstack-starter/build-guide/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.
<a href="https://agentmods.dev/rules/first-fluke/fullstack-starter/build-guide"><img src="https://agentmods.dev/badge/rules/first-fluke/fullstack-starter/build-guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00011 | $0.01215 |
| Opus 5.5 | $0.00004 | $0.00486 |
| Sonnet 5.5 | $0.00002 | $0.00243 |
| Haiku 4.5 | $0.00001 | $0.00121 |
Grade C, and why
build-guide scanned grade C 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 1mo 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf node_modules bun-lock.yaml How it starts
The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build Guide
Quick Start
Prerequisites
Ensure you have mise installed for runtime management.
# Install all runtimes
mise install
# Verify versions
mise current
Build Commands
This project uses mise monorepo mode with //path:task syntax.
Root (All Apps)
# List all available tasks
mise tasks --all
# Start all services
mise dev
# Lint all apps
mise lint
# Format all apps
mise format
# Test all apps
mise test
# Type check all apps
mise typecheck
# Build i18n files
mise i18n:build
# Generate OpenAPI schema and API clients
mise gen:api
API (apps/api)
# Start development server
mise //apps/api:dev
# Run tests
mise //apps/api:test
# Lint
mise //apps/api:lint
# Format
mise //apps/api:format
# Type check
mise //apps/api:typecheck
# Run DB migrations
mise //apps/api:migrate
# Create new migration
mise //apps/api:migrate:create
# Generate OpenAPI schema
mise //apps/api:gen:openapi
# Start local infrastructure (PostgreSQL, Redis, MinIO)
mise //apps/api:infra:up
# Stop local infrastructure
mise //apps/api:infra:down
# Build Docker image
docker build -t api apps/api
Web (apps/web)
# Start development server
mise //apps/web:dev
# Production build
mise //apps/web:build
# Run tests
mise //apps/web:test
# Lint
mise //apps/web:lint
# Format
mise //apps/web:format
# Type check
mise //apps/web:typecheck
# Generate API client from OpenAPI
mise //apps/web:gen:api
# Build Docker image
docker build -t web apps/web
Worker (apps/worker)
# Start worker
mise //apps/worker:dev
# Run tests
mise //apps/worker:test
# Lint
mise //apps/worker:lint
# Format
mise //apps/worker:format
# Build Docker image
docker build -t worker apps/worker
Mobile (apps/mobile)
# Run on device/simulator
mise //apps/mobile:dev
# Build
mise //apps/mobile:build
# Run tests
mise //apps/mobile:test
# Analyze (lint)
mise //apps/mobile:lint
# Format
mise //apps/mobile:format
# Generate localizations
mise //apps/mobile:gen:l10n
# Generate API client from OpenAPI
mise //apps/mobile:gen:api
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.
- 1mo ago Changed 97de5c11b28e
- 1mo ago First seen · 300 lines · 11 tokens per session scan C 366de443bfc6
build-guide is a cursor rule published in the GitHub repository first-fluke/fullstack-starter (224 stars, last pushed today), licensed MIT. It adds 11 tokens to every session and 1,215 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other cursor rules, from other repositories
schemas
Sanity schema and Studio config conventions.
docker
Docker Best Practices and Guidelines.
90-devops-deployment
Docker, CI/CD, AWS, Vercel, and VPS deployment rules.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.