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/mkmeral/containerized-strands-agents/agents-mdgit clone --depth 1 https://github.com/mkmeral/containerized-strands-agentsWrote 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/mkmeral/containerized-strands-agents/agents-md)<a href="https://agentmods.dev/instructions/mkmeral/containerized-strands-agents/agents-md"><img src="https://agentmods.dev/badge/instructions/mkmeral/containerized-strands-agents/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 | $0.03526 | $0.03526 |
| Opus 5 | $0.01763 | $0.01763 |
| Sonnet 5 | $0.00705 | $0.00705 |
| Haiku 4.5 | $0.00353 | $0.00353 |
Grade C, and why
containerized-strands-agents AGENTS.md scanned grade C with 1 finding 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.
Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
- `~/.aws/credentials` (read-only mount) How it starts
The opening of the file, as written. The whole thing — 366 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Overview
Containerized Strands Agents is an MCP (Model Context Protocol) server that hosts isolated Strands AI agents in Docker containers. Each agent runs independently with its own workspace, persists conversation history across restarts, and supports custom system prompts, per-agent tools, and GitHub integration. The fire-and-forget architecture enables autonomous background task execution while the host manages container lifecycle, idle timeouts, and session persistence.
Repository Structure
src/containerized_strands_agents/— Core package:server.py— MCP server (FastMCP tools)agent_manager.py— Docker orchestration, container lifecycleagent.py— Shared agent logic (create_agent, run_agent)cli.py— CLI commands (snapshot, restore, run)config.py— Configuration constants
docker/— Docker image: FastAPI runner, GitHub tools, requirementsui/— Optional web UI: FastAPI REST wrapper and HTML interfacescripts/— Shell scripts for building Docker image and running the servertests/— Unit, integration, and end-to-end tests using pytesttemplates/— GitHub Actions workflow template for running agents in CI.github/workflows/— CI and PyPI publishing workflowsdata/— Runtime persistence (gitignored): agent workspaces, sessions, task registry
Build & Development Commands
# Install in development mode
pip install -e ".[dev]"
# Install with web UI support
pip install -e ".[webui]"
# Or use Makefile
make dev # Install with all dependencies
make test # Run unit tests
make test-all # Run all tests (requires Docker)
make build # Build wheel and sdist
make docker # Build Docker image
# Build Docker image (auto-built on first use, or manually)
./scripts/build_docker.sh
# Run MCP server (for use with Kiro, Claude Desktop, etc.)
containerized-strands-agents-server
# or
python -m containerized_strands_agents.server
# Run web UI (finds free port 8000-8100)
containerized-strands-agents-webui
# Run tests
python -m pytest tests/ -v
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.
- 5d ago First seen · 366 lines · 3,526 tokens per session scan C cf71698ae995
containerized-strands-agents AGENTS.md is an instructions file published in the GitHub repository mkmeral/containerized-strands-agents (3 stars, last pushed 3mo ago), licensed MIT. It adds 3,526 tokens to every session, about $0.0176 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
devduck AGENTS.md
Instructions for cagataycali/devduck, covering agents.md — devduck, project: devduck, architecture, key design patterns and self-awareness.
laborforge-release CLAUDE.md
Claude Code instructions for EricLortie/laborforge-release, covering claude.md, first-run reality (read before setup — humans and agents), critical rules, never hardcode model names and docker-first development.
OwnPilot AGENTS.md
Instructions for ownpilot/OwnPilot, covering ownpilot, architecture, key patterns, commands and tech stack.
MoaV AGENTS.md
AGENTS.md instructions for MotherofallVPNs/MoaV, covering what moav is, install & run, everyday operations, dashboards & access — what to hand the owner and where things live.
SeekMoney-ai CLAUDE.md
Claude Code instructions for zykooooooooo/SeekMoney-ai, covering claude.md, project overview, development commands, development and production.
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.