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 neurawork-git/n8n-autopilot --skill build-workflowgit clone --depth 1 https://github.com/neurawork-git/n8n-autopilotWrote 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/neurawork-git/n8n-autopilot/build-workflow)<a href="https://agentmods.dev/skills/neurawork-git/n8n-autopilot/build-workflow"><img src="https://agentmods.dev/badge/skills/neurawork-git/n8n-autopilot/build-workflow/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/neurawork-git/n8n-autopilot/build-workflow"><img src="https://agentmods.dev/badge/skills/neurawork-git/n8n-autopilot/build-workflow.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 | $0.00085 | $0.04100 |
| Opus 5.5 | $0.00034 | $0.01640 |
| Sonnet 5.5 | $0.00017 | $0.00820 |
| Haiku 4.5 | $0.00009 | $0.00410 |
Grade A, and why
build-workflow 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 1mo 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 — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build Workflow (Full Pipeline)
Take a natural-language description and ship it as a verified live execution on n8n. All three phases are mandatory. The skill is only complete after a successful execution has been inspected and reported.
Companion plugin required. This skill leans on
n8n-as-code:n8n-architect(from then8nac-marketplaceplugin by Etienne Lescot) for schema research, authoring rules, and n8n best practices — installingn8n-autopilotwithout the companion plugin will work but you will miss the shared knowledge base. Install both:claude plugin marketplace add EtienneLescot/n8n-as-code claude plugin install n8n-as-code@n8nac-marketplace
Tools — all CLI
n8n-autopilot drives everything through the CLI (npx n8nac …) — use the table below. Since n8nac
2.4 a working MCP server exists (n8nac mcp, plus the read-only native-mcp assist against the
instance's own MCP endpoint — see docs/MCP.md); it complements research and
execution inspection but does NOT replace the CLI pipeline here: authoring stays .workflow.ts +
push, and live tests stay n8nac test (binary/file payloads NEVER go through MCP).
| Command | Role |
|---|---|
npx n8nac skills examples search "<q>" / info <id> / download <id> |
Community-template lookup (7000+ from n8nworkflows.xyz) — always Step 0 |
npx n8nac skills search "<q>" / node-info <name> --json / node-schema <name> --json |
Node discovery + exact TypeScript defs from local schemas |
npx n8nac skills related "<q>" / guides "<q>" |
Alternative nodes + tutorials |
npx n8nac skills validate <file> --strict --json |
Local workflow validation |
npx n8nac push <file> --verify |
Deploy + remote-state verification in one call |
npx n8nac test-plan <id> --json |
Infer triggerType + suggestedPayload before testing |
npx n8nac test <id> --data '...' |
HTTP-trigger live test (webhook/chat/form) |
npx n8nac execution get <execId> --include-data |
Inspect execution output |
npx n8nac find <q> --json --remote |
Search existing remote workflows |
npx n8nac workflow present <id> --json |
Resolve the user-facing n8n URL — never string-concat <host>/workflow/<id> |
npx n8nac workflow credential-required <id> |
Check credential readiness (exit 0 = all present, exit 1 = missing) |
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.
- 1mo ago First seen · 311 lines · 85 tokens per session scan A 09e88e5f8cf0
build-workflow is a skill published in the GitHub repository neurawork-git/n8n-autopilot (18 stars, last pushed 10d ago), licensed MIT. It adds 85 tokens to every session and 4,100 once invoked, about $0.0003 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.
Other skills, from other repositories
run-to-completion
Use when the work already in view in THIS conversation is an elaborate multi-step plan or spans several open projects AND most of the needed information is gathered, or when the user signals "autonomous" / "continuous" / "full auto" / "run to completion" / "keep going without stopping". Proactively offer to execute…
close-out-the-run
Use WHEN an unattended run is ending: the autonomous pile is exhausted, a resource limit is close, or the user has called a stop. Reconcile the durable records the run touched, stop cleanly at the gated boundary instead of churning, and write a wrap that says why each remaining item was left and how to resume it. Do…
n8n-to-langgraph
INVOKE THIS SKILL when converting n8n workflows to LangGraph applications, analyzing n8n workflow JSON files for conversion, or reviewing an n8n-to-LangGraph conversion. Covers the full pipeline: workflow analysis, architecture planning, implementation via ralph-loop, and review.
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. Also load when a live run you started for the user fails with an error from…
suggest-automations
Offer the three most common automations for a user as a single-choice card, from your own knowledge of their team and their apps, then build the one they choose once they confirm, or offer more. The system preloads it on onboarding threads, where the opening card already asked the user about themselves. Use it on…
add-teams
Adds Microsoft Teams connector to a Power Apps code app. Use when sending Teams messages, posting to channels, or integrating with Teams chat.