update

update is a skill for Claude Code, Codex from felipefontoura/bento. It costs 98 tokens per session (801 once invoked), scanned A, original, MIT.

A set of instructions for updating Bento and redeploying the services it manages on a remote server. Bento is a system for installing and running groups of applications on a VPS, or virtual private server.

In plain words
What is it for?
Use it to pull the latest Bento version and redeploy the existing application stacks on a server.
Why use it?
It provides checks and preserves the existing setup while applying newer Bento code. The update can briefly interrupt services and may reboot the server.

Skill for Claude CodeCodex

Part of the bento plugin — 13 skills shipped together

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 skills/felipefontoura/bento/update
Any agent
npx skills add felipefontoura/bento --skill update
Clone the repo
git clone --depth 1 https://github.com/felipefontoura/bento

Made for: Claude Code, Codex.

Or install bento, the plugin that ships this one along with the rest of its 13 skills.

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 update

README.md
[![agentmods](https://agentmods.dev/badge/skills/felipefontoura/bento/update.svg)](https://agentmods.dev/skills/felipefontoura/bento/update)
Your own site
<a href="https://agentmods.dev/skills/felipefontoura/bento/update"><img src="https://agentmods.dev/badge/skills/felipefontoura/bento/update.svg" alt="Measured on agentmods" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 801 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00098 $0.00801
Opus 5 $0.00049 $0.00400
Sonnet 5 $0.00020 $0.00160
Haiku 4.5 $0.00010 $0.00080

Measured 5d ago against content hash 409109b105f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

update scanned grade A 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.

Makes network callslowCapability

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

bash <(curl -sSL https://raw.githubusercontent.com/felipefontoura/bento/<ref>/boot.sh)"
plugins/bento/skills/update/SKILL.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are operating bento on a remote machine. An update redeploys running services (brief downtime) and may reboot the host. Confirm with the user before proceeding. All artifacts stay in English.

When to invoke

  • "update bento on <host>"
  • "pull the latest bento and redeploy"
  • "bump my server to the newest stacks"

If the user wants to add NEW apps (not update existing), use /bento:deploy. For a fresh server, /bento:install.

Pre-flight

  1. SSH reachable: ssh -o ConnectTimeout=5 "$user@$host" "echo SSH_OK".
  2. Confirm bento is installed: ssh "$user@$host" "test -f ~/.config/bento/state.json && echo BENTO_OK". If absent, stop.
  3. Read the saved bootstrap values so you re-apply with the SAME config:
    ssh "$user@$host" "jq -r '.bootstrap | .base_domain, .admin_email, .advertise_addr' ~/.config/bento/state.json"
    
  4. Ask which ref to update to (default stable; main or a feature branch only if the user asks).
  5. Confirm with the user: "This redeploys your running stacks (seconds of downtime each) and may reboot the VPS if a kernel/core library upgraded. Proceed?"

Update — unattended

Re-run the bootstrap one-liner unattended with the saved values. boot.sh re-clones the latest ref into ~/.local/share/bento, install.sh re-applies every step idempotently (hardening is a no-op when already done), reconciles state.stacks against Portainer, and redeploys the managed stacks.

ssh "$user@$host" "\
  BENTO_UNATTENDED=1 \
  BENTO_REF=<ref> \
  BENTO_BASE_DOMAIN=<base_domain> \
  BENTO_ADMIN_EMAIL=<admin_email> \
  ${ADVERTISE_ADDR:+BENTO_ADVERTISE_ADDR=$ADVERTISE_ADDR} \
  bash <(curl -sSL https://raw.githubusercontent.com/felipefontoura/bento/<ref>/boot.sh)"

If the run prints BENTO_REBOOT_SENTINEL, the VPS will reboot and the bento-resume.service unit continues on next boot — follow the "Post-hardening reboot" steps from the install skill (poll SSH back, then journalctl -u bento-resume.service -f).

Surgical alternative (no hardening pass, no reboot risk): the interactive Update menu does a git fetch + reset --hard and redeploys only stacks whose compose.yml/manifest.json changed. It is interactive and not cleanly scriptable over SSH — if the user wants that precise behaviour, tell them to run bash ~/.local/share/bento/install.sh and pick Update.

Read the full file on GitHub · 64 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. 5d ago First seen · 64 lines · 98 tokens per session scan A 409109b105f8

Subscribe to this mod's changes

update is a skill published in the GitHub repository felipefontoura/bento (20 stars, last pushed 1mo ago), licensed MIT. It adds 98 tokens to every session and 801 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

cloudflare-skill

Work with Cloudflare via the official cf CLI — check auth identity, list zones, list/create/delete DNS records, query the GraphQL Analytics API (zone traffic, Web Analytics/RUM), and run any other cf command. Output is parsed JSON.

zeenie-ai/OpenCompany · 55 tokens

gcloud-skill

Work with Google Cloud via the official gcloud CLI — check auth/config, list and switch projects, manage Compute Engine instances, deploy and inspect Cloud Run services, work with Cloud Storage, and run any other gcloud command. Output is parsed JSON.

zeenie-ai/OpenCompany · 55 tokens

vercel-skill

Deploy sites and apps to Vercel, inspect deployments, stream logs, and manage projects/env/domains via the Vercel CLI. Deploy a directory and get back the live deployment URL; everything else the CLI supports is available through the custom command passthrough.

zeenie-ai/OpenCompany · 59 tokens

nvcf-self-managed-installation

Install and operate NVCF self-hosted control-plane and separate compute-plane stacks. Covers Helmfile values and CLI profile installation flows, teardown, values overrides, pull secrets, and troubleshooting. Use for nvcf-self-managed-stack, nvcf-compute-plane-stack, split compute-plane installation, control-plane…

NVIDIA/nvcf · 110 tokens

nvcf-self-managed-prerequisite

Install the prerequisites the NVCA operator / compute plane needs before nvcf-nvca-install can succeed: the operator tool nvcf-cli (required by the compute-plane stack's register-cluster step), KAI Scheduler (for the KAIScheduler feature gate), and the SMB CSI driver (for the sharedStorage Samba sidecar PVCs). The two…

NVIDIA/nvcf · 195 tokens

portal-relay

Set up and run a public Portal relay on any Linux host with a public IP — Docker Compose deployment, embedded authoritative DNS with one-time NS delegation, optional TCP/UDP lease ports for game hosting, and registration in the public relay pool. Use when the user asks to run their own relay, contribute a relay to the…

gosuda/portal-tunnel · 111 tokens