config: Instructions file for Claude Code

CLAUDE.md

config CLAUDE.md is an instructions file for Claude Code, Codex from icefort-ai/config. It costs 1,633 tokens per session, scanned B, original, MIT.

Development instructions for the Snowfort Config project, a JavaScript or TypeScript codebase organized into packages and applications. They cover pnpm commands, builds, tests, linting, type checking, and a build-first web workflow.

In plain words
What is it for?
Use them when installing dependencies, building packages or apps, running checks, or managing the project's web development server.
Why use it?
They show contributors the project's expected commands and avoid using a live-reload workflow that the instructions say can cause timeouts. They also provide scripts for checking, starting, stopping, and inspecting the web server.

Instructions file for Claude CodeCodex

Written for Codex and Claude Code: reads ~/.codex or $CODEX_HOME, but also the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is icefort-ai/config's own configuration. It tells Claude Code and Codex how to work on config 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 config configures →

Reuse

Borrowing it

Nothing to install: this file belongs to icefort-ai/config. 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/icefort-ai/config/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/icefort-ai/config

Made for: Claude Code, Codex.

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 config CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/icefort-ai/config/claude-md.svg)](https://agentmods.dev/instructions/icefort-ai/config/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/icefort-ai/config/claude-md"><img src="https://agentmods.dev/badge/instructions/icefort-ai/config/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,633 This file is loaded in full into every session.
When invoked 1,633 The same file — it is already loaded in full.
Security scan B 2 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 $0.01633 $0.01633
Opus 5 $0.00816 $0.00816
Sonnet 5 $0.00327 $0.00327
Haiku 4.5 $0.00163 $0.00163

Measured 7d ago against content hash 99e414602bcd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

config CLAUDE.md scanned grade B with 2 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 7d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Current adapters: `ClaudeAdapter` (`~/.claude.json`), `CodexAdapter` (`~/.codex/config.json`)

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl http://localhost:4040/api/state
CLAUDE.md · 219 lines

How it starts

The opening of the file, as written. The whole thing — 219 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.

Essential Commands

Development Workflow

# Install dependencies (requires pnpm)
pnpm install

# Build all packages and apps
pnpm build

# Build only core package
pnpm --filter @snowfort/config-core run build

# Build only web app (includes server)
pnpm --filter @snowfort/config-web run build

# IMPORTANT: Web development uses build-first workflow
# NOT hot-reload like typical React apps

# For web development - USE THESE COMMANDS (they avoid timeouts):
./scripts/start.sh   # Quick start (exits immediately)
./scripts/status.sh  # Check if server is running
./scripts/stop.sh    # Stop server
./scripts/logs.sh    # View server output
./scripts/restart.sh # Restart server

# Run linting across all packages
pnpm lint

# Run type checking
pnpm typecheck

# Clean all build outputs
pnpm clean

Testing & Running

# Start web development server (RECOMMENDED - avoids timeouts)
./scripts/start.sh

# Check server status and health
./scripts/status.sh

# View server logs
./scripts/logs.sh

# Stop development server
./scripts/stop.sh

# Test CLI binary
node bin/sfconfig.js --help
node bin/sfconfig.js web
node bin/sfconfig.js web --port 3000

# Run tests
pnpm test

Server Management

# Start server (builds and starts, exits immediately)
./scripts/start.sh

# Check if server is running and healthy
./scripts/status.sh

# Stop server cleanly
./scripts/stop.sh

# Restart server (stop + start)
./scripts/restart.sh

# View server logs (recent)
./scripts/logs.sh

# Follow live logs
./scripts/logs.sh -f

# If port conflicts occur, use stop then start
./scripts/stop.sh && ./scripts/start.sh

API Testing

# Test API endpoints (server must be running)
curl http://localhost:4040/api/state
curl -X POST -H "Content-Type: application/json" \
  -d '{"claude-code": {"verbose": true}}' \
  http://localhost:4040/api/patch

Read the full file on GitHub · 219 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. 7d ago First seen · 219 lines · 1,633 tokens per session scan B 99e414602bcd

Subscribe to this mod's changes

config CLAUDE.md is an instructions file published in the GitHub repository icefort-ai/config (41 stars, last pushed 8mo ago), licensed MIT. It adds 1,633 tokens to every session, about $0.0082 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). 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

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 · 5,182 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

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

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

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 · 7,104 tokens