lad: Instructions file for Claude Code

CLAUDE.md

lad CLAUDE.md is an instructions file for Claude Code from franzvill/lad. It costs 1,251 tokens per session, scanned A, original, Apache-2.0.

Project instructions for LAD-A2A, a protocol and reference implementation that lets software agents discover one another on a local network. They describe the project, commands, tests, and development server.

In plain words
What is it for?
Use them to develop or test local agent discovery, including mDNS/DNS-SD, well-known discovery endpoints, security behavior, and the Python reference server.
Why use it?
They give an agent the project context and the exact commands needed to run tests or start the reference implementation safely during development.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is franzvill/lad's own configuration. It tells Claude Code how to work on lad 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 lad configures →

Reuse

Borrowing it

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

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.

agentmods badge for lad CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/franzvill/lad/claude-md/github.svg)](https://agentmods.dev/instructions/franzvill/lad/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/franzvill/lad/claude-md"><img src="https://agentmods.dev/badge/instructions/franzvill/lad/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.

agentmods 80×15 button for lad CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/franzvill/lad/claude-md"><img src="https://agentmods.dev/badge/instructions/franzvill/lad/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,251 This file is loaded in full into every session.
When invoked 1,251 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01251 $0.01251
Opus 5.5 $0.00500 $0.00500
Sonnet 5.5 $0.00250 $0.00250
Haiku 4.5 $0.00125 $0.00125

Measured 2mo ago against content hash 2fc0b5b57db1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

lad 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 2mo 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 · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 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.

Project Overview

LAD-A2A (Local Agent Discovery for A2A) is an open protocol specification and reference implementation for discovering A2A-capable AI agents on local networks. It enables AI agents to find and connect to service agents when joining networks (hotels, offices, hospitals, etc.).

Key concepts:

  • Discovery layer between physical networks and A2A protocol (MCP handles tools, A2A handles communication, LAD-A2A handles discovery)
  • Zero-configuration discovery via mDNS/DNS-SD (_lad-a2a._tcp.local), well-known endpoints (/.well-known/lad/agents), and DHCP
  • Security model assumes local networks are hostile by default

Common Commands

Reference Implementation

cd reference
python -m venv .venv && source .venv/bin/activate
pip install -e ".[dev]"

# Run tests (conformance, security, and v0.2 hardening)
pytest tests/ -v

# Run single test
pytest tests/test_lad.py::TestDiscoveryEndpoint::test_discovery_required_fields -v

# Start server (development only - no TLS)
python -m server.lad_server --name "My Agent" --port 8080

# Start server with TLS (production)
python -m server.lad_server --name "My Agent" --port 443 \
  --ssl-certfile /path/to/cert.pem --ssl-keyfile /path/to/key.pem

# Start server with AgentCard signing
python -m server.lad_server --name "My Agent" --signing-key keys/private.pem

# Run client
python -m client.lad_client --url http://localhost:8080

# Run client with verification
python -m client.lad_client --url https://agent.example.com \
  --signing-public-key keys/public.pem --require-verified

# Run client with interactive consent
python -m client.lad_client --url http://localhost:8080 --with-consent

# Generate signing keys
python -c "from common.signing import generate_signing_keys; generate_signing_keys('keys/')"

Demo Application

cd demo
cp .env.example .env  # Add OPENAI_API_KEY
./run_demo.sh         # Opens http://localhost:8000

Read the full file on GitHub · 127 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. 2mo ago First seen · 127 lines · 1,251 tokens per session scan A 2fc0b5b57db1

Subscribe to this mod's changes

lad CLAUDE.md is an instructions file published in the GitHub repository franzvill/lad (245 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 1,251 tokens to every session, about $0.0050 per session on Opus 5.5. 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.

Related

lad CLAUDE.md compared with instructions from other repositories

lad CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
lad CLAUDE.mdfranzvill/ladInstructions file2454mo agoApache-2.0A1,251Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode