yolo CLAUDE.md

yolo CLAUDE.md is an instructions file for coding agents from CoriChui/yolo. It costs 1,090 tokens per session, scanned A, original, MIT.

Fichier d’instructions qui décrit le fonctionnement de YOLO dans un dépôt de code. Il explique comment les demandes de fonctionnalités sont orientées, comment l’état du projet est stocké et où se trouvent les fichiers du cadre de travail.

In plain words
What is it for?
Il sert à guider la création de fonctionnalités, la résolution des chemins de fichiers et l’utilisation des étapes de planification et de validation de YOLO.
Why use it?
Il donne à l’agent de code les règles nécessaires pour suivre le processus du projet et s’arrêter aux étapes de validation prévues. Il réduit ainsi les décisions prises au mauvais endroit ou dans le mauvais format.

Instructions file

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/corichui/yolo/claude-md
Clone the repo
git clone --depth 1 https://github.com/CoriChui/yolo

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 yolo CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/corichui/yolo/claude-md.svg)](https://agentmods.dev/instructions/corichui/yolo/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/corichui/yolo/claude-md"><img src="https://agentmods.dev/badge/instructions/corichui/yolo/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,090 This file is loaded in full into every session.
When invoked 1,090 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.

ModelPer sessionOnce invoked
Fable 5 $0.01090 $0.01090
Opus 5 $0.00545 $0.00545
Sonnet 5 $0.00218 $0.00218
Haiku 4.5 $0.00109 $0.00109

Measured 3d ago against content hash 2fedc5e21895, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

yolo 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 3d 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 · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

YOLO workflow (this is a YOLO-initialized repo)

This project uses YOLO (reasoning-first). Feature state lives in git, not in tracked status files — see .claude/yolo/conventions.md. This block is the primary human-readable routing guide; the machine auto-triggers live in each skill's description. The confidence tiers and does-NOT-route taxonomy below are unique to this block.

File resolution: YOLO may be installed as a plugin. If ${CLAUDE_PLUGIN_ROOT} is set, resolve framework paths (.claude/yolo/..., .claude/skills/...) against it; otherwise read them project-relative. Project state (workspace/, this CLAUDE.md) is always project-local. See Where YOLO's files live in conventions.md.

Routing feature intent (auto-detect, then confirm at the gates)

When a prompt expresses intent to build / add / implement / create a feature, route it to the yolo-feature skill on your own — don't wait to be told "use YOLO." For feature intent this takes precedence over generic brainstorming. Auto-routing is safe because the cheap phase (intent capture + brief) is reversible and the plan gate stops before any expensive or irreversible work, so a wrong guess costs at most a throwaway brief.

Routes to yolo-feature (feature intent): "add CSV export", "build a settings page", "implement OAuth login", "create an endpoint for X", "support dark mode", "let users reset their password".

Does NOT route — handle normally (the common false positives):

  • Questions / understanding — "how does X work?", "where is Y?", "why does Z happen?". Answer directly; reach for yolo-research only if deeper code exploration helps.
  • Trivial edits — a typo, a one-line or single-file fix, a rename, a config tweak. Below the ceremony threshold: just make the edit, no brief.
  • Refactors / cleanups with no new user-facing capability — do them directly unless the user explicitly wants it tracked as a feature.
  • Bug reports — "X is broken", "fix the 500 on login" → route to yolo-debug for a systematic reproduce → isolate → fix → verify pass (a genuinely trivial one-line fix can still just be made). If the fix turns out to need new capability, yolo-debug hands off to yolo-feature.
  • Other YOLO acts — decisions, status, intake, roadmap (see Other intents).

Read the full file on GitHub · 69 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. 3d ago First seen · 69 lines · 1,090 tokens per session scan A 2fedc5e21895

Subscribe to this mod's changes

yolo CLAUDE.md is an instructions file published in the GitHub repository CoriChui/yolo (9 stars, last pushed 1mo ago), licensed MIT. It adds 1,090 tokens to every session, about $0.0054 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.

Related

Other instructions, from other repositories

docx-cli CLAUDE.md

Instructions for kklimuk/docx-cli, covering docx-cli, conventions, invariants, commands and testing.

kklimuk/docx-cli · 8,873 tokens

superdesign-skill AGENTS.md

Instructions for superdesigndev/superdesign-skill, covering project agent memory, what this repo is, skill flow invariant: two entry paths, ground truth for cli behavior and plugin packaging & release.

superdesigndev/superdesign-skill · 1,698 tokens

stewie-pixel guidelines

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

Stewie-pixel/claude-with-leetcode · 827 tokens

vanguard-frontier-agentic copilot-instructions.md

Instructions for VincentChuWaiChow/vanguard-frontier-agentic, covering vanguard frontier agentic repository instructions, what to optimize for, repo structure, rules for changes and cross-platform asset rule.

VincentChuWaiChow/vanguard-frontier-agentic · 359 tokens

archeyes CLAUDE.md

Instructions for thisAAY/archeyes, covering archeyes — project guide, layout, design system, commands and publishing a release.

thisAAY/archeyes · 1,284 tokens

kleinanzeigen-reader CLAUDE.md

Instructions for its-me-prash/kleinanzeigen-reader, covering claude.md — kleinanzeigen-reader, what this repo is, auto-load instructions for claude code, quick command reference and fetch a listing.

its-me-prash/kleinanzeigen-reader · 834 tokens