no-vibe: Instructions file for Claude Code

CLAUDE.md

no-vibe CLAUDE.md is an instructions file for Claude Code from rizukirr/no-vibe. It costs 2,788 tokens per session, scanned A, original, MIT.

A set of repository instructions for developing the no-vibe plugin, which teaches users by making them write project code themselves instead of having the AI write it. It explains the repository’s purpose, verification rules, and architecture across several AI command-line tools.

In plain words
What is it for?
Use it as guidance when changing the no-vibe plugin, its teaching behavior, its supported command-line tools, or its verification and architecture.
Why use it?
It prevents developers from confusing work on the plugin itself with using the plugin’s teaching mode. It also highlights two implementation layers that are easy to mix up.

Instructions file for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions CLAUDE.md; names the NotebookEdit tool; mentions Claude Code.

This is rizukirr/no-vibe's own configuration. It tells Claude Code how to work on no-vibe itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything no-vibe configures →

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

Reuse

Borrowing it

Nothing to install: this file belongs to rizukirr/no-vibe. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/rizukirr/no-vibe/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/rizukirr/no-vibe

Made for: Claude Code.

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.

agentmods badge for no-vibe CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rizukirr/no-vibe/claude-md/github.svg)](https://agentmods.dev/instructions/rizukirr/no-vibe/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/rizukirr/no-vibe/claude-md"><img src="https://agentmods.dev/badge/instructions/rizukirr/no-vibe/claude-md/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.

agentmods 80×15 button for no-vibe CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/rizukirr/no-vibe/claude-md"><img src="https://agentmods.dev/badge/instructions/rizukirr/no-vibe/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,788 This file is loaded in full into every session.
When invoked 2,788 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02788 $0.02788
Opus 5 $0.01394 $0.01394
Sonnet 5 $0.00558 $0.00558
Haiku 4.5 $0.00279 $0.00279

Measured 9d ago against content hash f16d4a45c59a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

no-vibe CLAUDE.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 9d 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.

CLAUDE.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Repo purpose

This repo is the no-vibe plugin itself — not a consumer of it. It ships tutor-style coding mode across five AI CLIs (Claude Code, OpenCode, Codex, Gemini CLI, Pi). When users install it, AI stops writing their project files and walks them through writing code themselves.

Do not confuse "developing this plugin" with "being in no-vibe mode". Editing files inside this repo is normal plugin development — the no-vibe write guard does not apply here unless .no-vibe/active exists at the repo root.

What no-vibe is for (read before changing teaching behavior)

no-vibe is pure for learning. It is a productive constraint, not a feature limitation. The plugin exists because vibe-coding — letting AI write code while the user watches — produces output without producing understanding, and copy-typing what the AI shows reproduces the same hollow outcome one keystroke at a time. The thing that actually transfers is the user's thought process: deciding what to do, predicting what will happen, naming what broke. no-vibe is built so the user contributes that, not just keystrokes.

  • The user writes every line of project code. AI refuses to. That's the hard guard, enforced by hooks across all five surfaces.
  • The user thinks before they type. Guided write is the default disclosure mode — AI walks the user toward the code in English with graded help verbs (hint / analogy / pseudo / show / less) so the code they write comes from a decision they made, not a block they transcribed. Showcase exists as a fallback but is not the path that produces learning.
  • The user predicts before they run. Every Phase 3 layer ends with a one-question prediction gate targeting an edge case, intermediate value, branch, or failure mode — never a value already named in the expected-output signature. The run becomes a self-test, not passive verification.
  • The user learns from the project they are actually building. Not contrived exercises, not toy examples — the real codebase, the real bugs, the real architectural decisions in front of them. Teaching is in situ.
  • AI is a Socratic guide, not a code generator. It asks questions, gives hints scaled to the learner's level, reviews what the user wrote, and explains how things work when the user is ready to integrate the explanation.
  • Learning is bottom-up and incremental. Six phases (0–6), broken into layers, each layer a small unit the user can write themselves. Progress is observable in the user's actual diff and in the prediction-gate answers logged across the session.

Read the full file on GitHub · 116 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.

  1. 9d ago First seen · 116 lines · 2,788 tokens per session scan A f16d4a45c59a

Subscribe to this mod's changes

no-vibe CLAUDE.md is an instructions file published in the GitHub repository rizukirr/no-vibe (36 stars, last pushed 2mo ago), licensed MIT. It adds 2,788 tokens to every session, about $0.0139 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.

Related

Other instructions, from other repositories

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens