What is vibeauracle AGENTS.md?

Project instructions for contributors and coding agents working on VibeAuracle, a keyboard-focused terminal and editor tool for AI-assisted software work. They describe its design principles, supported runtimes, and contribution rules.

Use them when changing VibeAuracle code, choosing where new functionality belongs, working with its terminal interface or agent runtimes, and checking contribution practices.

They give contributors shared guidance about how the project is structured and how changes should fit its system-aware, modular design. They also help prevent unwanted files and unsuitable build output from entering the repository.

vibeauracle AGENTS.md — Instructions file for Codex and OpenCode by nathfavour: Project instructions for contributors and coding agents work

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 instructions/nathfavour/vibeauracle/agents-md

Clone the repo

git clone --depth 1 https://github.com/nathfavour/vibeauracle

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/nathfavour/vibeauracle/agents-md.svg)](https://agentmods.dev/instructions/nathfavour/vibeauracle/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/nathfavour/vibeauracle/agents-md"><img src="https://agentmods.dev/badge/instructions/nathfavour/vibeauracle/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 864 This file is loaded in full into every session.

When invoked 864 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5	$0.00864	$0.00864
Opus 5	$0.00432	$0.00432
Sonnet 5	$0.00173	$0.00173
Haiku 4.5	$0.00086	$0.00086

Measured 4d ago against content hash 2f08157573c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vibeauracle 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 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.

AGENTS.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🤖 VibeAuracle Agentic Context

Welcome, Agent. You are operating within VibeAuracle, a Distributed, System-Intimate AI Engineering Ecosystem. This project is built by and for AI-augmented engineers who value deep integration with the underlying operating system and hardware.

🌌 Project Essence

VibeAuracle is not just a CLI; it's a "God-tier" engineering companion that unifies the terminal, the IDE, and the AI assistant into a single, keyboard-centric experience.

Core Philosophy

System Intimacy: The agent must be aware of the environment (CWD, CPU, VRAM, OS) before suggesting or taking action.
Modular Runtimes: We support multiple agentic engines (Internal Vibe loop, official Copilot SDK, and custom personas).
Keyboard-First: The UI (TUI) is optimized for speed and fluidity, using the Bubble Tea framework.
Hexagonal Architecture: The core logic (internal/brain) is decoupled from adapters (providers, tools, UI) to allow infinite extensibility.

🛠️ Development Guidelines

For AI & Human Contributors

No Binaries in Git: NEVER commit binaries, executables, or build artifacts to the repository.
Build Isolation: All local builds must be directed to the /build/ directory (which is git-ignored). Create the directory if it does not exist.
Strict Go Patterns: We use Go Workspaces. Maintain decoupling between modules. Go 1.21 is the intentional minimum version to ensure the project remains buildable from source on older environments; do not upgrade the toolchain requirement unless explicitly discussed.
Dependency Integrity: Significant effort has been invested in pinning specific versions (e.g., quic-go, libp2p, qpack) to resolve complex dependency conflicts. Tampering with these versions is heavily frowned upon and should only be performed when absolutely necessary to fix future breaking errors or security vulnerabilities.
Security First: Never expose secrets. Use the vault module. Tool execution requires explicit intent awareness.
TUI Integrity: UI changes must adhere to the Bubble Tea (TEA) pattern. Styling is done via Lipgloss.
No Unauthorized PRs: NEVER create, submit, or merge Pull Requests without explicit, per-action permission from the user.
Branch Management: NEVER create new feature branches or delete any existing branches. All work must be performed on the branch designated by the user.
Automated Commits: We leverage autocommiter, an external tool, to manage commits to GitHub for this project. This prevents human and/or AI agents from being confused by changes that are already committed/synced without manual git commit calls.
Agentic Responsibility: When acting as an agent, prioritize executeToolCalls for multi-step tasks. Use the official Copilot SDK runtime (/agent /sdk) for high-stakes engineering.

Read the full file on GitHub · 48 lines

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.

4d ago First seen · 48 lines · 864 tokens per session scan A 2f08157573c1

Subscribe to this mod's changes

vibeauracle AGENTS.md is an instructions file published in the GitHub repository nathfavour/vibeauracle (5 stars, last pushed 2mo ago), licensed MIT. It adds 864 tokens to every session, about $0.0043 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 2026-08-31.

collaborate communityexchange github-copilot github-pages student-vscode

stridetastic CLAUDE.md

Claude Code instructions for 0wulf/stridetastic, covering project overview, purpose, key features, architecture and system architecture.

0wulf/stridetastic · 10,148 tokens

spec-kitty AGENTS.md

AGENTS.md instructions for Priivacy-ai/spec-kitty, covering spec kitty development guidelines, ⚠️ critical: load the project charter first, ⚠️ critical: template source location, ⚠️ critical: use canonical sources, never improvise and ⚠️ critical: git workflow — no direct pushes to origin/main.

Priivacy-ai/spec-kitty · 9,910 tokens

vibeauracle AGENTS.md