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-workflow-v2git 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-v2)<a href="https://agentmods.dev/skills/neurawork-git/n8n-autopilot/build-workflow-v2"><img src="https://agentmods.dev/badge/skills/neurawork-git/n8n-autopilot/build-workflow-v2/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-v2"><img src="https://agentmods.dev/badge/skills/neurawork-git/n8n-autopilot/build-workflow-v2.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 | $0.00116 | $0.01846 |
| Opus 5 | $0.00058 | $0.00923 |
| Sonnet 5 | $0.00023 | $0.00369 |
| Haiku 4.5 | $0.00012 | $0.00185 |
Grade A, and why
build-workflow-v2 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 12d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build Workflow v2 — JS-Orchestrated (deterministic gates)
Same outcome as build-workflow + deploy: ship a verified live execution on n8n. Difference: the pipeline is a Claude Code Workflow JS script, not prose. The script body is the control flow; each step is a small typed subagent (agents/n8n-*.md) that runs the real npx n8nac … command and returns structured output.
Why v2
Prose pipelines are soft — the model is told to validate before push, told "max 3 cycles", told never claim a fix before inspecting the execution. v2 makes those structural:
| Soft (prose v1) | Hard (v2 JS) |
|---|---|
| "validate, then push" | if (!validate.passed) { fix-loop } — push unreachable until passed |
| "max 3 fix cycles" | while (cycle <= 3) — a real counter |
| "ALWAYS test after push" | Test phase only reachable after push.verified === true |
| "Push ≠ Fix" | status:'success' only returned after the execution is inspected — no other path emits it |
Boundary: the script enforces that gates run in order and loops are bounded — not that the authored TS is correct. The n8n-node-verifier fan-out guards correctness (kills the #1 runtime killer: a guessed param key n8n silently ignores).
Architecture — roles are extracted, not inline
The orchestrator scripts hold only control flow + schemas + one-line tasks. Every subagent's role, CLI rules, tools, and model live in a reusable agent definition:
| agentType | Role | Tools |
|---|---|---|
n8n-researcher |
plan: sync folder, template lookup, node discovery, trigger, test data | read + Bash |
n8n-node-verifier |
adversarial param contract for one node type | read + Bash |
n8n-comprehender |
pull/read existing workflow, summarize shape + change site (EDIT) | read + Bash |
n8n-author |
write / edit / fix the .workflow.ts |
read/write + Bash |
n8n-validator |
validate --strict --json gate |
read + Bash |
workflow-reviewer |
design-quality gate (HTTP-in-Code, masked errors, AI sub-node miswiring) the validator can't catch | read + Bash |
n8n-deployer |
drift-aware push --verify gate |
read + Bash |
n8n-tester |
test-plan classify, credential check, live test, execution inspect | read + Bash |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 103 lines · 116 tokens per session scan A 7c1b1ccf7186
build-workflow-v2 is a skill published in the GitHub repository neurawork-git/n8n-autopilot (18 stars, last pushed 1mo ago), licensed MIT. It adds 116 tokens to every session and 1,846 once invoked, about $0.0006 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
n8n-agents
Design n8n AI agents the right way. Use when building or editing any @n8n/n8n-nodes-langchain. AI node — an AI Agent, LLM chain, Text Classifier, or Information Extractor — and whenever the user mentions AI agents, LLM with tools, tool calling, $fromAI, system prompts, agent memory, sessionId, structured/JSON output…
n8n-mcp-tools-expert
Expert guide for using n8n-mcp MCP tools effectively. Use when searching for nodes, validating configurations, accessing templates, managing workflows, organizing workflows into folders, managing credentials, auditing instance security, or using any n8n-mcp tool. Provides tool selection guidance, parameter formats…
n8n-subworkflows
Build reusable, composable n8n sub-workflows. Use when extracting shared logic, building anything multi-step or reused across workflows, or any workflow over 10 nodes — and whenever the user mentions sub-workflows, Execute Workflow, reuse, shared/common logic, modular workflows, "Define Below" inputs…
n8n-validation-expert
Interpret validation errors and guide fixing them. Use when encountering validation errors, validation warnings, false positives, operator structure issues, or need help understanding validation results. Also use when asking about validation profiles, error types, the validation loop process, or auto-fix capabilities.…
n8n-workflow-patterns
Proven workflow architectural patterns from real n8n workflows. Use when building new workflows, designing workflow structure, choosing workflow patterns, planning workflow architecture, or asking about webhook processing, HTTP API integration, database operations, AI agent workflows, batch processing, or scheduled…
n8n-binary-and-data
Handle files and binary data in n8n correctly. Use when working with files, images, PDFs, attachments, uploads or downloads, base64, vision/multimodal input, or when an AI agent needs a file as tool input or output — and whenever the user mentions $binary, binaryPropertyName, "read the PDF", "attach the file", "send…