What is Containarium CLAUDE.md?

A set of instructions for AI assistants working on Containarium, a software platform with command-line tools, APIs, and container-based services. It defines rules for public documentation, typed interfaces, and how assistants should work.

Use it when changing Containarium code, documentation, API contracts, command-line workflows, or service integrations.

It prevents sensitive deployment names from appearing in public files and discourages fragile string-based interfaces. It also keeps development work aligned with the project’s command-line and API conventions.

How FootprintAI/Containarium configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to FootprintAI/Containarium. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/FootprintAI/Containarium/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/FootprintAI/Containarium

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/footprintai/containarium/claude-md/github.svg)](https://agentmods.dev/instructions/footprintai/containarium/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/footprintai/containarium/claude-md"><img src="https://agentmods.dev/badge/instructions/footprintai/containarium/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/footprintai/containarium/claude-md"><img src="https://agentmods.dev/badge/instructions/footprintai/containarium/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,621 This file is loaded in full into every session.

When invoked 1,621 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01621	$0.01621
Opus 5.5	$0.00648	$0.00648
Sonnet 5.5	$0.00324	$0.00324
Haiku 4.5	$0.00162	$0.00162

Measured 2mo ago against content hash ebf5c19fd1e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Containarium 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 2mo 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 · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Containarium — guidance for Claude / AI assistants

This file is a small set of durable conventions for AI assistants working on this repository. Keep it short — only rules whose violation we'd actually want to catch in review.

No instance / endpoint / tenant names in OSS-visible files

This repository is public-facing. Anonymize anything that names a specific deployment in files that ship with the repo: docs/, README.md, CHANGELOG.md, design notes, runbooks, PR descriptions, and commit messages.

Don't write	Do write
Concrete backend / lab node hostnames	"a backend host" / `<host>` / "the GPU node"
Live production cluster apex hostnames	"the cluster's apex hostname" / `<cluster>.example.com`
Tenant container names (`<tenant>-container` with real tenants)	"a tenant container" / `<tenant>-container` (generic)
Containarium-core service container names (in operator-specific context)	"the platform Postgres LXC" / "core service LXCs"
Live IPs (LAN, GCP, Tailscale)	"a private LAN IP" / `<sentinel-ip>`
Internal tenant workload names (docker container, app names)	"a tenant workload" / "a docker compose service"

Why: concrete names are reconnaissance signals — they reveal what's running where, which workloads to target, which backend names to fingerprint. The cost of generic wording is one extra word; the cost of leaking is permanent — PR descriptions and merged commits stay indexed forever.

Where concrete names ARE fine:

Private operator runbooks not in the repo.
Internal Slack / email / private docs.
Operator memory files outside the repo.

Before pushing any doc / runbook / PR description: grep the diff for concrete names; if you're not sure, anonymize.

CLI-first, MCP wraps it

When adding a new platform action (anything that mutates Containarium state — create, expose, route, deploy, etc.):

Land it as a containarium <verb> cobra subcommand under internal/cmd/<verb>.go first.
The MCP tool in internal/mcp/tools.go is a thin wrapper over the same underlying Go function used by the CLI handler. Don't have the MCP tool call an HTTP endpoint that the CLI doesn't.

Read the full file on GitHub · 144 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.

2mo ago First seen · 144 lines · 1,621 tokens per session scan A ebf5c19fd1e5

Subscribe to this mod's changes

Containarium CLAUDE.md is an instructions file published in the GitHub repository FootprintAI/Containarium (316 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,621 tokens to every session, about $0.0065 per session on Opus 5.5. 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.

agent-native agent-sandbox agentic-ai lxc multi-tenant ssh

Containarium CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Containarium CLAUDE.mdFootprintAI/Containarium	Instructions file	316	yesterday	Apache-2.0	A	1,621	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

Containarium: Instructions file for Claude Code