defang CLAUDE.md

defang CLAUDE.md is an instructions file for coding agents from DefangLabs/defang. It costs 63 tokens per session, scanned A, original, MIT.

Project instructions for Defang, a command-line tool that deploys Docker Compose applications to cloud platforms.

In plain words
What is it for?
They are for guiding coding-agent work in the Defang repository and applying the right rules when relevant files are opened.
Why use it?
They tell Claude Code to load the shared agent guidance, while keeping extra rules specific to Claude Code in their own files.

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/defanglabs/defang/claude-md
Clone the repo
git clone --depth 1 https://github.com/DefangLabs/defang

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 defang CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/defanglabs/defang/claude-md.svg)](https://agentmods.dev/instructions/defanglabs/defang/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/defanglabs/defang/claude-md"><img src="https://agentmods.dev/badge/instructions/defanglabs/defang/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 63 This file is loaded in full into every session.
When invoked 63 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 $0.00063 $0.00063
Opus 5 $0.00032 $0.00032
Sonnet 5 $0.00013 $0.00013
Haiku 4.5 $0.00006 $0.00006

Measured 5d ago against content hash 77e3485c039b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

defang 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 5d 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 · 8 lines

What it actually says

@AGENTS.md

Claude Code

Claude Code reads CLAUDE.md, not AGENTS.md, so this file imports the shared agent guide above.

Additional Claude-specific rules live in .claude/rules/ and are path-scoped so detailed guidance only loads when relevant files are opened.

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. 5d ago First seen · 8 lines · 63 tokens per session scan A 77e3485c039b

Subscribe to this mod's changes

defang CLAUDE.md is an instructions file published in the GitHub repository DefangLabs/defang (167 stars, last pushed today), licensed MIT. It adds 63 tokens to every session, about $0.0003 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.