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 skills add felipefontoura/bento --skill n8ngit 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/n8n)<a href="https://agentmods.dev/skills/felipefontoura/bento/n8n"><img src="https://agentmods.dev/badge/skills/felipefontoura/bento/n8n/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.
<a href="https://agentmods.dev/skills/felipefontoura/bento/n8n"><img src="https://agentmods.dev/badge/skills/felipefontoura/bento/n8n.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00154 | $0.01730 |
| Opus 5 | $0.00077 | $0.00865 |
| Sonnet 5 | $0.00031 | $0.00346 |
| Haiku 4.5 | $0.00015 | $0.00173 |
Grade A, and why
n8n 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You operate an n8n instance already deployed by bento — but you drive it
through the n8n-mcp server, never through n8n's raw REST API. bento
deploys both stacks together: n8n (editor + worker + webhook) and n8n-mcp
(an MCP server that wraps n8n with full node schemas and validation). This is
day-2 work: building and operating workflows. You do NOT redeploy the stacks —
that is /bento:deploy. All artifacts stay in English.
Golden rule — operate via
n8n-mcp, not the raw API. The n8n-mcp tools carry every node's property schema, run validation before deploy, and encode the tedious API rules (connection shapes, expression syntax, credential wiring). Hand-rollingPOST /api/v1/workflowsskips all of that and produces workflows that import but don't run. Use the MCP tools.
When to invoke
- "build / automate in n8n", "wire a workflow", "add/configure a node"
- "validate / fix / autofix my workflow", "why doesn't my workflow run"
- "list / run / inspect my workflows and executions"
For getting n8n running use /bento:deploy.
Discover the instance — don't hardcode
ssh "$user@$host" "jq -r '.envs.\"n8n-mcp\".N8N_MCP_HOST' \$HOME/.config/bento/state.json" # MCP endpoint host
ssh "$user@$host" "jq -r '.envs.\"n8n-mcp\".N8N_MCP_AUTH_TOKEN' \$HOME/.config/bento/state.json" # Bearer (don't echo)
ssh "$user@$host" "jq -r '.envs.n8n.N8N_HOST' \$HOME/.config/bento/state.json" # editor (UI)
ssh "$user@$host" "jq -r '.envs.n8n.N8N_WEBHOOK_HOST' \$HOME/.config/bento/state.json" # webhook host
- MCP endpoint:
https://<N8N_MCP_HOST>/mcp(Streamable HTTP) or/sse. Auth:Authorization: Bearer <N8N_MCP_AUTH_TOKEN>. - The n8n-mcp talks to n8n internally with an n8n API key (a JWT minted in
n8n → Settings → n8n API), wired at deploy as
N8N_MCP_N8N_API_KEY. Without it then8n_*API tools are disabled and only the read-only node/template tools work. - Editor UI =
https://<N8N_HOST>. Webhooks/MCP-trigger workflows are served fromhttps://<N8N_WEBHOOK_HOST>— a different host than the editor.
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.
- 9d ago First seen · 105 lines · 154 tokens per session scan A 5af034f4d9ff
n8n is a skill published in the GitHub repository felipefontoura/bento (20 stars, last pushed 1mo ago), licensed MIT. It adds 154 tokens to every session and 1,730 once invoked, about $0.0008 per session on Opus 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.
Other skills, from other repositories
intent-recognition
Classifies automation requests using two decisions: anchor (which primitive owns the top-level control flow — workflow-anchored, agent-anchored, needs-clarification, or out-of-scope) and embedsother (whether the other primitive appears embedded inside — an agent step inside a workflow, or a workflow invoked as an…
post-build-flow
Handles workflow verification and setup after build-workflow succeeds, or when the message contains workflow-verification-follow-up or workflow-setup-required. Load after direct builds, when verificationReadiness requires action, or on orchestrator verify/setup follow-up turns.
planned-task-runtime
Handles system follow-up turns: planned-task-follow-up (synthesize, replan, build-workflow, checkpoint), background-task-completed, running-tasks context, and create-tasks silence rules. Load whenever any of these tags appear or after calling create-tasks.
config-evals
Builds and maintains configuration-based evaluations on a workflow with the eval-config tool. Use when the user asks to set up, add, view, change, or remove an evaluation, score, grade, or judge a workflow's output, or measure answer quality against a test dataset. This is the only eval form Instance AI handles — it…
one-off-operations
Handles one-off operations: the request is a concrete effect that happens once — export or copy data somewhere, a migration, a backfill, a cleanup — with no trigger, schedule, or reuse intent. The workflow is the vehicle, not the deliverable. Users rarely say "one-off"; infer it from the task's shape. Load before…
debugging-executions
Debug failed or wrong-output workflow executions using executions tools. Load when the user reports execution failures, unexpected node output, empty parameter values after a successful run, or a node showing a red or failed expression error.