What is bcherny-claude CLAUDE.md?

A project instruction file for Claude Code, an AI assistant that works on software repositories. It records the project’s structure, coding rules, development workflow, and commands for checking changes.

Use it to document project context, preferred TypeScript style, error handling, testing expectations, linting and formatting commands, and the steps to review work before committing or opening a pull request.

It gives the assistant consistent guidance about how the repository should be changed and verified. This reduces repeated explanations and helps prevent the same mistakes from happening again.

How 0xquinto/bcherny-claude configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to 0xquinto/bcherny-claude. 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/0xquinto/bcherny-claude/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/0xquinto/bcherny-claude

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/0xquinto/bcherny-claude/claude-md/github.svg)](https://agentmods.dev/instructions/0xquinto/bcherny-claude/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/0xquinto/bcherny-claude/claude-md"><img src="https://agentmods.dev/badge/instructions/0xquinto/bcherny-claude/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/0xquinto/bcherny-claude/claude-md"><img src="https://agentmods.dev/badge/instructions/0xquinto/bcherny-claude/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 926 This file is loaded in full into every session.

When invoked 926 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	$0.00926	$0.00926
Opus 5	$0.00463	$0.00463
Sonnet 5	$0.00185	$0.00185
Haiku 4.5	$0.00093	$0.00093

Measured 10d ago against content hash 41095bb0b484, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

bcherny-claude 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 10d 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 · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md - Project Instructions for Claude Code

This file provides project-specific guidance for Claude Code. Update this file whenever Claude does something incorrectly so it learns not to repeat mistakes.

Project Overview

(Describe your project here)

Development Workflow

Give Claude verification loops for 2-3x quality improvement:

Make changes
Run typecheck
Run tests
Lint before committing
Before creating PR: run full lint and test suite

Code Style & Conventions

Prefer type over interface; never use enum (use string literal unions instead)
Use descriptive variable names
Keep functions small and focused
Write tests for new functionality
Handle errors explicitly, don't swallow them

Commands Reference

# Verification loop commands (customize for your project)
npm run typecheck        # Type checking
npm run test            # Run tests
npm run lint            # Lint all files
npm run format          # Format code

# Git workflow
git status              # Check current state
git diff                # Review changes before commit

Self-Improvement

After every correction or mistake, update this CLAUDE.md with a rule to prevent repeating it. Claude is good at writing rules for itself.

End corrections with: "Now update CLAUDE.md so you don't make that mistake again."

Keep iterating until the mistake rate measurably drops.

Working with Plan Mode

Start every complex task in plan mode (shift+tab to cycle)
Pour energy into the plan so Claude can 1-shot the implementation
When something goes sideways, switch back to plan mode and re-plan. Don't keep pushing.
Use plan mode for verification steps too, not just for the build

Auto Mode

Boris Cherny's current #1 tip: run in auto mode — no permission prompts.

Cycle to auto mode with shift+tab (default → auto-accept → plan mode)
Auto mode is the building block for multi-clauding: start a session, and while it runs unattended, work on another session in parallel
Pair it with worktrees (/worktree, claude -w) and subagents so parallel sessions don't collide
Make it sticky by setting the default permission mode (defaultMode) in .claude/settings.json
Keep the guardrails when running unattended: scoped allow-lists in settings.json, worktrees for isolation, and the Stop hook that nudges a session to keep going

Read the full file on GitHub · 113 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.

10d ago First seen · 113 lines · 926 tokens per session scan A 41095bb0b484

Subscribe to this mod's changes

bcherny-claude CLAUDE.md is an instructions file published in the GitHub repository 0xquinto/bcherny-claude (356 stars, last pushed 3mo ago), licensed MIT. It adds 926 tokens to every session, about $0.0046 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.

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

bcherny-claude: Instructions file for Claude Code