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 skills/felipefontoura/bento/contribute-stacknpx skills add felipefontoura/bento --skill contribute-stackgit clone --depth 1 https://github.com/felipefontoura/bentoWrote 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/skills/felipefontoura/bento/contribute-stack)<a href="https://agentmods.dev/skills/felipefontoura/bento/contribute-stack"><img src="https://agentmods.dev/badge/skills/felipefontoura/bento/contribute-stack.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 | $0.00110 | $0.03572 |
| Opus 5 | $0.00055 | $0.01786 |
| Sonnet 5 | $0.00022 | $0.00714 |
| Haiku 4.5 | $0.00011 | $0.00357 |
Grade A, and why
contribute-stack 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 4d 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.
on purpose: `wget`-based probes on small VPS were SIGKILLing healthy How it starts
The opening of the file, as written. The whole thing — 344 lines — stays where its author put it; the contents beside it link to each section on GitHub.
contribute-stack
Use this skill when a CONTRIBUTOR asks to add a new application stack to the
bento repo. Always start by reading CLAUDE.md for current conventions —
prefer its rules over anything stated here if they ever drift.
Context guard — check before doing anything. This skill operates on a local clone of the bento repo: it creates files under
stacks/, editsREADME.md, and makes a git commit. Confirm you are in that context —CLAUDE.mdand astacks/app/directory must exist in the working tree:test -f CLAUDE.md && test -d stacks/app && echo BENTO_REPO_OKIf that fails, STOP. This is a contributor skill, not an operator one. The user is probably trying to deploy an app onto their own VPS — point them at the bento plugin's
/bento:deployskill, which does it over SSH without a local clone. Do not try to scaffold files outside a bento checkout.
Every comment, message, and doc you produce must be in English. Even when the user prompts you in Portuguese, the artifacts going into the repo stay English-only.
When to invoke
Trigger phrases include:
- "add a new stack for "
- "I want to bundle into bento"
- "create a stack: "
- "scaffold "
If the user is just asking to deploy an existing stack via the menu,
that is not this skill — point them at Step 3 in the install menu.
Required inputs
Ask for these up front if missing:
- Stack key — short, kebab-case, lowercase (e.g.
n8n,cli-proxy-api). Will be the directory name and the user-visible label in the menu. - Upstream GitHub repo —
<owner>/<repo>(e.g.n8n-io/n8n). This is non-negotiable: the skill fetches the project's own referencedocker-compose.ymland.env.examplebefore writing anything. - Public-facing host — does this app expose an HTTP UI/API behind
Traefik? If yes, the default host pattern is
<key>.${BASE_DOMAIN}. If no, no Traefik labels are needed.
Everything else (image tag, env vars, secrets, dependencies, ports, healthcheck endpoint) is derived from the upstream repo in step 1 below — do not invent any of it from training data.
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.
- 4d ago First seen · 344 lines · 110 tokens per session scan A 023d53de8608
contribute-stack is a skill published in the GitHub repository felipefontoura/bento (20 stars, last pushed 1mo ago), licensed MIT. It adds 110 tokens to every session and 3,572 once invoked, about $0.0006 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.
Other skills, from other repositories
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…
portainer-mcp-hygiene
How to drive the Portainer MCP server's tools correctly — both reading and mutating. Reading: project responses with select (JMESPath), where the heavy fields live (snapshots, status blocks, managed fields), how to handle non-JSON Docker/K8s proxy endpoints (container and pod logs, stats, exec), and how to interpret…
portainer-mcp-release
How to cut a portainer-mcp release that bumps the embedded Portainer OpenAPI spec to a new Portainer minor (e.g. 2.41.x → 2.42.x). Walks through finding the upstream patch target, regenerating the spec, recounting ops/tags per profile, refreshing the orphan-tag inventory, bumping version pins across the README and…
byaan:start
Initialize Byaan development environment using Docker. Builds and starts backend and frontend containers with SQLite, opens the browser, learns the codebase, and configures MCP. Use when setting up the project for the first time.
config-var
Use when adding, renaming, or removing an environment variable, changing startup configuration validation, adding a Compose profile or service, or adding a Prometheus metric. Triggers on "environment variable", "NACRE", "config", "docker compose", "profile", "metrics", "healthcheck", "readiness".
node-deploy
Build and deploy Node.js applications — version detection, package managers, framework-specific builds, monorepo support, and Dockerfile patterns. Use when deploying a Node.js, JavaScript, or TypeScript project, or when package.json is detected in the repository.