What is greywall CLAUDE.md?

Project instructions for Greywall, a command-line sandbox that limits what commands can access on a computer and redirects network traffic through a controlled proxy.

Use them to set up Greywall, build and run it, execute tests, format Go code, and run static analysis and security checks.

They give coding agents and developers consistent commands for building, testing, formatting, and checking the project before changes are committed.

How GreyhavenHQ/greywall configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to GreyhavenHQ/greywall. 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/GreyhavenHQ/greywall/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/GreyhavenHQ/greywall

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/greyhavenhq/greywall/claude-md.svg)](https://agentmods.dev/instructions/greyhavenhq/greywall/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/greyhavenhq/greywall/claude-md"><img src="https://agentmods.dev/badge/instructions/greyhavenhq/greywall/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 749 This file is loaded in full into every session.

When invoked 749 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.

Model	Per session	Once invoked
Fable 5.1	$0.00749	$0.00749
Opus 5	$0.00375	$0.00375
Sonnet 5	$0.00150	$0.00150
Haiku 4.5	$0.00075	$0.00075

Measured 6d ago against content hash 52758c486d07, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

greywall 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 6d 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 · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Greywall

Deny-by-default command sandbox. Wraps commands with restricted filesystem access (current directory only by default) and transparent network redirection through greyproxy. Supports --learning mode to trace filesystem access and auto-generate config templates. Linux (bubblewrap + seccomp/Landlock/eBPF) and macOS (sandbox-exec Seatbelt profiles).

Build & Run

make setup          # install deps + lint tools (first time)
make build          # compile binary (downloads tun2socks)
make run            # build and run
./greywall --help   # CLI usage

Test

make test           # all unit + integration tests
make test-ci        # with coverage and race detection (-race -coverprofile)
GREYWALL_TEST_NETWORK=1 ./scripts/smoke_test.sh ./greywall  # smoke tests

Lint & Format

make fmt            # format with gofumpt
make lint           # golangci-lint (staticcheck, errcheck, gosec, govet, revive, gofumpt, misspell, etc.)

Always run make fmt && make lint before committing.

Project Structure

cmd/greywall/          CLI entry point
internal/
  config/              Configuration loading & validation
  platform/            OS detection
  sandbox/             Platform-specific sandboxing (~7k lines)
    manager.go         Sandbox lifecycle orchestration
    command.go         Command blocking/allow lists
    linux.go           bubblewrap + bridges (ProxyBridge, DnsBridge)
    macos.go           sandbox-exec Seatbelt profiles
    linux_seccomp.go   Seccomp BPF syscall filtering
    linux_landlock.go  Landlock filesystem control
    linux_ebpf.go      eBPF violation monitoring
    sanitize.go        Environment variable hardening
    dangerous.go       Protected files/dirs lists
pkg/greywall/          Public Go API
docs/                  Full documentation
scripts/               Smoke tests, benchmarks, release

Code Conventions

Language: Go 1.25+
Formatter: gofumpt (enforced in CI)
Linter: golangci-lint v2 (config in .golangci.yml)
Import order: stdlib, third-party, local (github.com/GreyhavenHQ/greywall)
Platform code: build tags (//go:build linux, //go:build darwin) with *_stub.go for unsupported platforms
Error handling: custom error types (e.g., CommandBlockedError)
Logging: stderr with [greywall:component] prefixes
Config: JSON with comments (via tidwall/jsonc), optional pointer fields for three-state booleans

Read the full file on GitHub · 80 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.

6d ago First seen · 80 lines · 749 tokens per session scan A 52758c486d07

Subscribe to this mod's changes

greywall CLAUDE.md is an instructions file published in the GitHub repository GreyhavenHQ/greywall (291 stars, last pushed 23d ago), licensed Apache-2.0. It adds 749 tokens to every session, about $0.0037 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.

LLM Security agents claude-code macos opencode sandbox

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 · 5,182 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

greywall: Instructions file for Claude Code