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 instructions/obviousworks/vibe-coding-ai-rules/agents-mdgit clone --depth 1 https://github.com/obviousworks/vibe-coding-ai-rulesWrote 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/instructions/obviousworks/vibe-coding-ai-rules/agents-md)<a href="https://agentmods.dev/instructions/obviousworks/vibe-coding-ai-rules/agents-md"><img src="https://agentmods.dev/badge/instructions/obviousworks/vibe-coding-ai-rules/agents-md.svg" alt="Measured on agentmods" 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 | $0.02396 | $0.02396 |
| Opus 5 | $0.01198 | $0.01198 |
| Sonnet 5 | $0.00479 | $0.00479 |
| Haiku 4.5 | $0.00240 | $0.00240 |
Grade A, and why
vibe-coding-ai-rules AGENTS.md 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - Universal AI Agent Configuration
This file follows the AGENTS.md standard, supported by Cursor, GitHub Copilot, Codex, Aider, and other AI coding tools. Place this file in your project root and customize the sections below for your project.
[Project Name]
Project Overview
[Brief description of the project's purpose and core functionality]
Architecture: [e.g., Microservices, Monolith, JAMstack] Domain: [e.g., E-commerce, Healthcare, Finance] Scale: [e.g., Startup MVP, High-traffic production, Enterprise]
Tech Stack
Core Technologies
- Language: [Python 3.11+, TypeScript 5.x, etc.]
- Framework: [FastAPI, Next.js, Spring Boot, etc.]
- Database: [PostgreSQL 15, MongoDB 6, etc.]
- Cache: [Redis 7, Memcached, etc.]
- Package Manager: [npm, pnpm, pip, poetry, etc.]
Key Dependencies
- [Library/Framework]: [Version and purpose]
- [Library/Framework]: [Version and purpose]
Development Tools
- Linter: [ESLint, Pylint, etc.]
- Formatter: [Prettier, Black, etc.]
- Type Checker: [TypeScript, mypy, etc.]
- Testing: [Vitest, pytest, JUnit, etc.]
Setup Commands
# Install dependencies
[install command]
# Setup environment
cp .env.example .env
# Edit .env with required values
# Database setup
[migration commands]
# Start development server
[dev command]
Build and Development Commands
File-Scoped Commands (Preferred - Fast)
# Type check single file (3 seconds)
[command] path/to/file.ext
# Format single file
[command] path/to/file.ext
# Lint single file
[command] path/to/file.ext
# Run single test file
[command] path/to/test.ext
Project-Wide Commands (Use Sparingly)
# Full type check (2 minutes)
[command]
# Full test suite (3 minutes)
[command]
# Full build (5 minutes)
[command]
Important: Always use file-scoped commands for checking individual changes. Only run project-wide commands when explicitly requested or before final commit.
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.
- 3d ago First seen · 336 lines · 2,396 tokens per session scan A 9ac8d9ad4cc4
vibe-coding-ai-rules AGENTS.md is an instructions file published in the GitHub repository obviousworks/vibe-coding-ai-rules (88 stars, last pushed 2mo ago), licensed MIT. It adds 2,396 tokens to every session, about $0.0120 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.
Other instructions, from other repositories
n.codes AGENTS.md
Instructions for yungookim/n.codes, covering repository guidelines, core architecture principle: agentic ui generation, project structure & module organization, cli module organization (cli/lib/) and build, test, and development commands.
n.codes CLAUDE.md
Instructions for yungookim/n.codes, a project described as: Let users generate features with prompts in your app.
Vibe-Coding-Dev-Setup general.instructions.md
Instructions for AndreasKarz/Vibe-Coding-Dev-Setup, covering trust boundary, project general coding standards, application structure, architecture overview and technology stack.
Vibe-Coding-Dev-Setup tests.instructions.md
Instructions for AndreasKarz/Vibe-Coding-Dev-Setup, covering general guidelines, test naming conventions, test data and setup, test structure and assertions.
Vibe-Coding-Dev-Setup graphql.instructions.md
Instructions for AndreasKarz/Vibe-Coding-Dev-Setup, covering graphql layer rules, layer separation, implementation-first approach, attribute stacking order and dataloader convention.
Vibe-Coding-Dev-Setup worker.instructions.md
Instructions for AndreasKarz/Vibe-Coding-Dev-Setup, covering worker layer rules, consumer design, observability, error handling and quartz jobs.