bento: Instructions file for Claude Code

CLAUDE.md

bento CLAUDE.md is an instructions file for Claude Code from felipefontoura/bento. It costs 8,013 tokens per session, scanned F, original, MIT.

Repository-specific contribution instructions for bento, including its purpose, architecture, documentation rules, and language requirements. A repository is a code project with its files, history, and development conventions.

In plain words
What is it for?
Use it before making substantial changes to the bento repository, especially changes to its application stacks, libraries, conventions, architecture, or documentation.
Why use it?
It helps contributors understand the project quickly and avoid changes that conflict with its documentation or English-only user-facing text requirements.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is felipefontoura/bento's own configuration. It tells Claude Code how to work on bento itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything bento configures →

Reuse

Borrowing it

Nothing to install: this file belongs to felipefontoura/bento. 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/felipefontoura/bento/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/felipefontoura/bento

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.

agentmods badge for bento CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/felipefontoura/bento/claude-md.svg)](https://agentmods.dev/instructions/felipefontoura/bento/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/felipefontoura/bento/claude-md"><img src="https://agentmods.dev/badge/instructions/felipefontoura/bento/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 8,013 This file is loaded in full into every session.
When invoked 8,013 The same file — it is already loaded in full.
Security scan F 4 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.08013 $0.08013
Opus 5 $0.04006 $0.04006
Sonnet 5 $0.01603 $0.01603
Haiku 4.5 $0.00801 $0.00801

Measured 7d ago against content hash 8c5c6bece192, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade F, and why

bento CLAUDE.md scanned grade F with 4 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 7d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

sudo docker exec "$cid" <your-bootstrap-command>

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

A user runs **one** `curl | bash` command, then a guided 3-step menu

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf ~/.config/bento ~/.local/state/bento ~/.local/share/bento

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

A user runs **one** `curl | bash` command, then a guided 3-step menu
CLAUDE.md · 754 lines

How it starts

The opening of the file, as written. The whole thing — 754 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Maintainer guide for the bento repository. Read this before touching anything. It is loaded automatically by Claude Code when you work in this repo and is meant to be equally useful for any human contributor.


English only. Every user-facing message (prompts, log lines, error output, README, CLAUDE.md, code comments) must be in English. We have users outside Brazil; mixed-language strings break documentation tools and look unprofessional. If you catch a pt-BR leak, fix it on sight.

Docs stay in sync with code. Any change deeper than a one-line bug fix — a new stack, a behaviour change, a convention reversal, a path rename, a removed file — must be reflected in the docs in the same PR. Specifically:

  • New / removed stack → update the table in README.md and the stacks/ ASCII tree in this file.
  • Convention change (healthchecks, logging, secrets, deploy block, etc.) → update the "Quality bar" table and the "How to add a new application stack" section here, and the relevant guidance in .claude/skills/contribute-stack/SKILL.md.
  • New library file under lib/ → add it to the architecture box and the lib/ ASCII tree below.
  • External-facing behaviour (env vars, flags, prompts, report contents) → update README.md.

If a maintainer notices doc drift before code drift, fix it the same way. The rule is "no PR leaves the docs misleading."

What this repo is

bento is an all-in-one installer that takes a fresh Ubuntu/Debian VPS to "production-ready apps running" through a guided interactive menu. It is not a generic Docker Swarm stack collection — it is an opinionated platform where every stack is parametrized, generated, and deployed through a single tool.

A user runs one curl | bash command, then a guided 3-step menu (Harden → Infra → Apps) leaves them with a hardened host, Traefik + Portainer with TLS, and the apps they picked, each ready for first login.

Read the full file on GitHub · 754 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. 7d ago First seen · 754 lines · 8,013 tokens per session scan F 8c5c6bece192

Subscribe to this mod's changes

bento CLAUDE.md is an instructions file published in the GitHub repository felipefontoura/bento (20 stars, last pushed 1mo ago), licensed MIT. It adds 8,013 tokens to every session, about $0.0401 per session on Opus 5. A static security scan graded it F with 4 findings (asks for root, downloads and executes remote code, recursive force delete). 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

vscode buildNext.instructions.md

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

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

langchain AGENTS.md

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 · 4,469 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

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 · 7,104 tokens