container-use AGENTS.md

A project instruction file for Container-Use, a tool that gives coding agents isolated development environments. Each environment combines a Git branch, a Dagger container, a separate working directory, and operation records.

In plain words
What is it for?
Use it when building, testing, or modifying Container-Use, especially its environment tools, Dagger integration, branches, worktrees, or operation logs.
Why use it?
It requires all work inside those environments to use their environment tools, which helps preserve isolation and project history. It also tells agents how users can view or retrieve the work.

Instructions file for CodexOpenCode

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/dagger/container-use/agents-md
Clone the repo
git clone --depth 1 https://github.com/dagger/container-use

Made for: Codex, OpenCode.

Per session 2,214 This file is loaded in full into every session.
When invoked 2,214 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 $0.02214 $0.02214
Opus 5 $0.01107 $0.01107
Sonnet 5 $0.00443 $0.00443
Haiku 4.5 $0.00221 $0.00221

Measured 2d ago against content hash 19c96c7228b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

container-use 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 2d 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.

AGENTS.md · 260 lines

How it starts

The opening of the file, as written. The whole thing — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Guidelines for Container-Use

Core Architecture

Container-use provides isolated, containerized development environments for AI agents by combining:

  • Git branches for each environment (e.g., adjective-animal names like fluffy-lion)
  • Dagger containers with code mounted at /workdir
  • Git notes (container-use and container-use-state refs) for operation logging and state persistence
  • Worktrees in ~/.config/container-use/worktrees/ for filesystem representation

Key Principle: All operations MUST go through environment tools - NEVER use git commands directly in environments.

Critical Agent Rules (MUST FOLLOW)

  1. Use ONLY environment tools for ANY and ALL file, code, or shell operations - NO EXCEPTIONS
  2. DO NOT install or use git CLI with environment_run_cmd tool - environment tools handle git integration automatically
  3. ALWAYS inform user how to view your work: cu log <env-id> and cu checkout <env-id>
  4. Failure to inform user makes work inaccessible to others

Build, Test, and Lint Commands

Build

# Build binary
go build -o container-use ./cmd/container-use

# Using Dagger
dagger call build --platform=current export --path ./container-use

Test

# Run all tests
go test ./...

# Unit tests only (fast, no containers)
go test -short ./...

# Integration tests
go test -count=1 -v ./environment

# Run single test
go test -run TestSpecificFunction ./path/to/package
go test -run TestSpecificFunction -v ./path/to/package

# Run tests in specific package
go test ./repository
go test ./environment

Format and Lint

# Format code (REQUIRED before committing)
go fmt ./...

# Lint
dagger call lint

Dependencies

# Install dependencies
go mod download

# Clean up dependencies
go mod tidy

Code Style Guidelines

Imports

  • Order: stdlib imports first, then third-party imports
  • Group blank lines between stdlib and third-party
  • No unused imports (checked by linter)
  • Example:
    import (
        "context"
        "fmt"
        "os"
    
        "dagger.io/dagger"
        "github.com/spf13/cobra"
    )
    

Read the full file on GitHub · 260 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. 2d ago First seen · 260 lines · 2,214 tokens per session scan A 19c96c7228b7

Subscribe to this mod's changes

container-use AGENTS.md is an instructions file published in the GitHub repository dagger/container-use (4,027 stars, last pushed 15d ago), licensed Apache-2.0. It adds 2,214 tokens to every session, about $0.0111 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.

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

buildNext

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

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

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

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 · 7,040 tokens

langchain 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 · 4,345 tokens