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/dagger/container-use/agents-mdgit clone --depth 1 https://github.com/dagger/container-useWhat 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 | $0.02214 | $0.02214 |
| Opus 5 | $0.01107 | $0.01107 |
| Sonnet 5 | $0.00443 | $0.00443 |
| Haiku 4.5 | $0.00221 | $0.00221 |
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.
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-animalnames likefluffy-lion) - Dagger containers with code mounted at
/workdir - Git notes (
container-useandcontainer-use-staterefs) 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)
- Use ONLY environment tools for ANY and ALL file, code, or shell operations - NO EXCEPTIONS
- DO NOT install or use git CLI with environment_run_cmd tool - environment tools handle git integration automatically
- ALWAYS inform user how to view your work:
cu log <env-id>andcu checkout <env-id> - 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" )
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.
- 2d ago First seen · 260 lines · 2,214 tokens per session scan A 19c96c7228b7
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.
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.
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).
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.
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).
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.
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.