What is vibe-racer CLAUDE.md?

Instructions for vibe-racer, a command-line tool that runs software tasks through fixed stages involving an AI coding session and human review points. It ends with code that has been tested and committed to Git, a system for tracking code changes.

Use it to initialize and run tasks, move them through the pipeline, inspect or coordinate work, validate changes, and run the project's development commands.

It gives software tasks a defined workflow, so progress, reviews, validation, branches, commits, and secret checks follow one process.

How teripaquitinho/vibe-racer configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to teripaquitinho/vibe-racer. 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/teripaquitinho/vibe-racer/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/teripaquitinho/vibe-racer

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/teripaquitinho/vibe-racer/claude-md/github.svg)](https://agentmods.dev/instructions/teripaquitinho/vibe-racer/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/teripaquitinho/vibe-racer/claude-md"><img src="https://agentmods.dev/badge/instructions/teripaquitinho/vibe-racer/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/teripaquitinho/vibe-racer/claude-md"><img src="https://agentmods.dev/badge/instructions/teripaquitinho/vibe-racer/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 476 This file is loaded in full into every session.

When invoked 476 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.

Model	Per session	Once invoked
Fable 5.1	$0.00476	$0.00476
Opus 5	$0.00238	$0.00238
Sonnet 5	$0.00095	$0.00095
Haiku 4.5	$0.00048	$0.00048

Measured 12d ago against content hash 815fa9054faf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

vibe-racer 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 12d 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 · 42 lines

What it actually says

vibe-racer

CLI that runs structured AI pipelines ("races") on software tasks using Claude Code SDK. Each task moves through a fixed state machine — alternating between human pit stops and AI-driven laps — ending in committed, tested code.

Key docs

Pipeline stages & architecture: docs/how-it-works.md
All CLI commands: docs/commands.md
Configuration (.vibe-racer.yml): docs/configuration.md
Roadmap: backlog.md

Project structure

src/
  cli/          # commander commands (init, new, drive, pitwall, radio, fasten)
  pipeline/     # state machine, handlers per stage, validation
  claude/       # SDK session runner, prompt builder, tool guard, fasten analysis
  state/        # task discovery, state.yml read/write, advancement logic
  git/          # branch management, commits, secret scanning
  config/       # .vibe-racer.yml parsing

Dev commands

npm run dev          # run CLI via tsx (no build needed)
npm run build        # tsup → dist/
npm run test         # vitest run
npm run typecheck    # tsc --noEmit
npm run lint         # eslint src/

Key decisions

No runtime dependency on host project — vibe-racer is a standalone CLI; it only reads the host project's README.md / CLAUDE.md as context.
State lives in plans/NNNN_slug/state.yml — never in memory; every command re-reads state from disk.
One branch per task (vibe-racer/NNNN_slug) — created automatically on first drive, never pushed automatically.
Persona per lap — system prompt is extended with a role-specific persona (Product Designer / Architect / Engineer) depending on the current stage.
Tool guard — canUseTool in src/claude/guard.ts enforces security rules on every SDK tool call.
Trivial fast-path — tasks with trivial: true in state.yml skip product and design laps, going directly from objective review to plan questions.

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.

12d ago First seen · 42 lines · 476 tokens per session scan A 815fa9054faf

Subscribe to this mod's changes

vibe-racer CLAUDE.md is an instructions file published in the GitHub repository teripaquitinho/vibe-racer (5 stars, last pushed 18d ago), licensed MIT. It adds 476 tokens to every session, about $0.0024 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.

Claude Code Git and workflow ai ai-agents claude cli developer-tools

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.

github/spec-kit · 7,126 tokens

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

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

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

vibe-racer: Instructions file for Claude Code