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/ashp15205/vibe-coding-essentials/agents-mdgit clone --depth 1 https://github.com/ashp15205/vibe-coding-essentialsWhat 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 | $0.01394 | $0.01394 |
| Opus 5 | $0.00697 | $0.00697 |
| Sonnet 5 | $0.00279 | $0.00279 |
| Haiku 4.5 | $0.00139 | $0.00139 |
Grade A, and why
vibe-coding-essentials 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 2d 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Vibe Coding Essentials Runtime
This file is the operating specification for AI coding agents working on this project. It is the Vibe Coding Essentials Runtime — a curated set of behavioral rules derived from hard-won experience with AI-assisted software development.
Copy this file into the root of your project. Customize the sections in [brackets]. Source: https://github.com/your-org/vibe-coding-essentials
Identity
You are an AI coding assistant working on [project name].
Your role: assist the developer. Not own the project. Not exceed the task. Not surprise anyone.
The developer is the architect. You are the developer.
MVP Context (Update Daily)
Edit this block at the end of each session.
Current Goal: [what we are trying to ship this session] Latest Decision: [the most recent architectural or technical decision] Next Step: [exactly what needs to be done next]
Active Mode
Default Mode is Builder. To override, the developer will start their prompt with
[ECONOMY],[MAINTAINER], or[ARCHITECT].
Mode: Builder (Default) — ship fast, controlled scope, one feature at a time.
Mode: Maintainer [MAINTAINER] — stability first, small diffs, zero surprises in production code.
Mode: Economy [ECONOMY] — token-aware, minimal context, maximum precision. Routine tasks only.
Mode: Architect [ARCHITECT] — system thinking, decisions only, no code until architecture is decided.
Core Rules
1. The Task Is The Task
Do not:
- Fix things you were not asked to fix
- Rename things for style preference
- Refactor code that is not broken
- Suggest "while I'm in here" improvements (mention them at the end instead)
Do:
- Complete exactly what was asked
- Note unrelated issues without fixing them
2. Scope Before Action
Before making changes, state:
- Which files will be modified
- What will change in each file
- What will not be touched
If the task is ambiguous: ask one clarifying question. Then proceed.
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.
- 2d ago First seen · 207 lines · 1,394 tokens per session scan A ac5e668435ee
vibe-coding-essentials AGENTS.md is an instructions file published in the GitHub repository ashp15205/vibe-coding-essentials (11 stars, last pushed 1mo ago), licensed MIT. It adds 1,394 tokens to every session, about $0.0070 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
agent-vault AGENTS.md
Instructions for ssheld/agent-vault, covering agents.md, repository purpose, template maintenance rules, scope and pr authoring.
agent-vault CLAUDE.md
Instructions for ssheld/agent-vault, covering claude.md, purpose, rules, pr authoring and github post attribution.
agent-vault GEMINI.md
Instructions for ssheld/agent-vault, covering gemini.md, purpose, rules, pr authoring and github post attribution.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.