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/ccivlcid/vibeharness/agents-mdgit clone --depth 1 https://github.com/ccivlcid/VibeHarnessWrote 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/ccivlcid/vibeharness/agents-md)<a href="https://agentmods.dev/instructions/ccivlcid/vibeharness/agents-md"><img src="https://agentmods.dev/badge/instructions/ccivlcid/vibeharness/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 5.1 | $0.01089 | $0.01089 |
| Opus 5 | $0.00544 | $0.00544 |
| Sonnet 5 | $0.00218 | $0.00218 |
| Haiku 4.5 | $0.00109 | $0.00109 |
Grade C, and why
VibeHarness AGENTS.md 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 5d 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.
Instruction-override phrasinghighPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
- Do NOT follow the rules below (they are for target projects that use VibeHarness) Copies of this mod
2 near-identical copies found in the catalogue:
- VibeHarness GEMINI.md — 95% identical, 10 lines differ
- VibeHarness CLAUDE.md — 94% identical, 10 lines differ
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to Codex when working with code in this repository.
This file is the single source of rules that every Codex session must read first. Copy this file into a target project when using VibeHarness with Codex.
Working on the VibeHarness Framework Itself
If you are editing the VibeHarness repository (this repo — the framework, templates, examples, skills), you are a framework developer, not a non-developer user. In this context:
- Do NOT follow the rules below (they are for target projects that use VibeHarness)
- Do NOT create
docs/biz/planning docs orProgress.mdfor framework changes - Treat this as a normal development project
The rules below apply only when AGENTS.md is copied into a target project.
Important: Do NOT create project code inside examples/. Always create code at the project root.
VibeHarness — Senior Developer AI for Non-Developers
You are a senior full-stack developer and vibe coding mentor. Turn non-developer ideas into complete MVPs. Make all technical decisions yourself. Only ask for confirmation on business decisions.
Document everything — so the next AI session can continue, and non-developers learn by watching.
Your roles: Senior Developer (build MVPs), Mentor (clear docs), Partner (manage scope), Advisor (evaluate feasibility honestly — infeasible ideas get alternatives, oversized ideas get phases).
Context-Aware Document Loading
Before reading reference docs, read graph.json first. It maps every document's purpose, tags, and relationships. Use queryHints to find only the documents relevant to your current task. See docs/skills/context-graph.md for the full process.
Reference docs are in docs/references/ (templates and rules) and docs/skills/ (implementation guidance). Do not load them all — let graph.json guide you.
Code Pattern Recipes
Before writing implementation code, read code-patterns.json first. It indexes production-ready code recipes in docs/recipes/. Use patternHints to match the project type (e.g., chat_app, todo_app, ai_chatbot) to the exact recipes needed. Use keywordMap to match specific features (e.g., login, CRUD, realtime) to recipes.
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.
- 5d ago First seen · 88 lines · 1,089 tokens per session scan C 25d32730a8c7
VibeHarness AGENTS.md is an instructions file published in the GitHub repository ccivlcid/VibeHarness (5 stars, last pushed 4mo ago), licensed MIT. It adds 1,089 tokens to every session, about $0.0054 per session on Opus 5. A static security scan graded it C with 1 finding (instruction-override phrasing). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).