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.
npx agentmods add instructions/defanglabs/defang/agents-mdgit clone --depth 1 https://github.com/DefangLabs/defangWrote 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.
[](https://agentmods.dev/instructions/defanglabs/defang/agents-md)<a href="https://agentmods.dev/instructions/defanglabs/defang/agents-md"><img src="https://agentmods.dev/badge/instructions/defanglabs/defang/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00656 | $0.00656 |
| Opus 5 | $0.00328 | $0.00328 |
| Sonnet 5 | $0.00131 | $0.00131 |
| Haiku 4.5 | $0.00066 | $0.00066 |
Grade A, and why
defang AGENTS.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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Defang CLI Agent Guide
Keep this file short. It is loaded at startup by coding agents, so it should contain only rules that matter for most tasks.
Repository Basics
- This repository contains the Defang CLI, a Go command-line tool under
src/. - The root
Makefiledelegates tosrc/Makefile. - Work from
src/for Go commands unless a root command explicitly delegates there. - For deeper architecture context, read
docs/agent-reference.mdon demand instead of expanding this file.
Common Commands
- Build:
cd src && make build - Unit tests:
cd src && make testorcd src && go test -short ./... - Focused package test:
cd src && go test -short ./pkg/cli/compose/... - Lint:
cd src && make lint - Auto-fix lint:
cd src && make lint-fix - Tidy modules:
cd src && make tidy - Regenerate protos after editing
fabric.proto:cd src && make protos
Agent Enforcement
- Before committing Go changes, run
cd src && make lint. - If lint fails, run
cd src && make lint-fix, then rerun lint. - Before pushing Go changes, run
cd src && make testunless the user explicitly scopes verification differently. - Do not use
--no-verifyto bypass hooks. - If a required tool is missing in the environment, say exactly what could not run.
Go Change Quality
- Make the smallest coherent change that fixes the root problem.
- Put behavior in the package that owns the concept: commands orchestrate, session/stack code selects stacks, compose code loads compose projects, provider code handles cloud behavior.
- Avoid adding exported functions, options, or struct fields for one-off behavior.
- Do not split one invariant across packages unless that boundary already exists.
- Reuse existing Defang abstractions and standard library helpers before adding new helpers.
- Keep CLI commands thin: parse flags, construct existing managers, call domain logic, print results.
- Return real errors with context. Ignore missing optional files only when missing is the documented contract.
- Keep provider-generic code generic; provider-specific behavior belongs behind provider-specific implementations or explicit parameters.
- Comments should explain why, not restate what the code does.
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.
- 3d ago First seen · 55 lines · 656 tokens per session scan A bab391d8ca96
defang AGENTS.md is an instructions file published in the GitHub repository DefangLabs/defang (164 stars, last pushed 6d ago), licensed MIT. It adds 656 tokens to every session, about $0.0033 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.
Other instructions, from other repositories
ecspresso CLAUDE.md
Instructions for kayac/ecspresso, covering claude.md, project overview, git workflow, build commands and build the binary.
wordpress-nginx-docker-compose CLAUDE.md
Claude Code instructions for urre/wordpress-nginx-docker-compose, covering claude.md, what this is, architecture, two .env files — don't confuse them and common commands.
sftp-cc CLAUDE.md
Claude Code instructions for toohamster/sftp-cc, covering claude.md, project overview, architecture, key design decisions and testing changes.
langchain-aws AGENTS.md
Instructions for langchain-ai/langchain-aws, covering global development guidelines for the langchain monorepo, project architecture and context, langchain-aws structure, key components and langgraph-checkpoint-aws structure.
mcp-ssh-manager CLAUDE.md
Instructions for bvisible/mcp-ssh-manager, covering claude.md, project overview, architecture, commands and setup and installation.
aws-bench AGENTS.md
Instructions for aws-bench/aws-bench, covering agents.md, setup, commands, project structure and code style.