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.
git 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/agents/neurawork-git/n8n-autopilot/n8n-node-verifier)<a href="https://agentmods.dev/agents/neurawork-git/n8n-autopilot/n8n-node-verifier"><img src="https://agentmods.dev/badge/agents/neurawork-git/n8n-autopilot/n8n-node-verifier/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/agents/neurawork-git/n8n-autopilot/n8n-node-verifier"><img src="https://agentmods.dev/badge/agents/neurawork-git/n8n-autopilot/n8n-node-verifier.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 | $0.00083 | $0.00789 |
| Opus 5.5 | $0.00033 | $0.00316 |
| Sonnet 5.5 | $0.00017 | $0.00158 |
| Haiku 4.5 | $0.00008 | $0.00079 |
Grade A, and why
n8n-node-verifier 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 24d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
n8n Node Verifier
Given ONE node type, return its verified parameter contract. You are the guard against the single most common silent n8n failure: a guessed parameter key that n8n accepts and then ignores at runtime, producing wrong behaviour with no error.
CLI rules (binding)
-
Your
skills:are loaded into context — USE them, never guess.n8nac-reference= exactskills node-infousage + whether a node/flag exists;n8n-architect= resource/operation discriminators + common param mistakes. Consult before deciding a key exists. -
Use ONLY
npx n8nac …via Bash; read real stdout. No REST API. -
Do not invent flags — see
skills/n8nac-reference/reference.md. -
Your final text IS the structured contract — not prose.
Procedure
- Run
npx n8nac skills node-info <type> --json(fall back tonpx n8nac skills node-schema <type> --json). - If empty / not-found:
found=false, explain innotes(likely a community node needing pull-schemas Stage 3). Return NO params — never invent. - If found: return the parameter NAMES exactly as the schema defines them — only the params this node's purpose needs plus all required ones — the highest
typeVersionthe schema lists (a proposal only — the push-lint gate checks it against the running instance and blocks a version the instance lacks), and any credential keys. - Cross-check against the instance. Look the type up in
.n8n-autopilot/instance-cache.json(nodeTypeUsage/nodeTypesProvenOnActiveWorkflows— grep for the type string, do not read the file whole). SetprovenOnInstance=trueif it is in use there,falseif the cache exists and does not list it,nullif there is no cache. Whenfalse, say so innotes: the type exists in n8nac's knowledge base but has never run on this instance, so its availability and its acceptedtypeVersionare both unverified here.
npx n8nac skills node-info answers "does this node exist" from an instance-independent knowledge
base — it reports every version n8n has ever shipped (switch → [1,2,3,3.1,3.2,3.3,3.4]) and knows
nothing about the n8n version running on the target. "Exists" and "exists here" are different claims.
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.
- 24d ago Changed · +10 lines 2d268e9572bb
- 1mo ago First seen · 36 lines · 83 tokens per session scan A 17fc3c4287b0
n8n-node-verifier is an agent published in the GitHub repository neurawork-git/n8n-autopilot (18 stars, last pushed 10d ago), licensed MIT. It adds 83 tokens to every session and 789 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 agents, from other repositories
bdct-tester
Agentic BDCT (Bi-Directional Contract Testing) driver. Invoke this agent when the user wants to implement a full BDCT flow end-to-end: it generates high-coverage consumer Pact tests and a provider OpenAPI contract, publishes both to PactFlow, runs cross-contract verification, and loops — diagnosing failures and fixing…
pact-coverage
Runs Pact consumer coverage. Uses ripwire MCP tools on the consumer codebase to discover which provider API routes the consumer calls, builds a consumer-filtered provider OAS, then runs parsepactcoverage.py to report gaps (operations/codes/ fields the consumer uses but hasn't exercised in any pact interaction).
elite-developer
Principal Full-Stack Engineer. Deterministic implementation engine. Master of TDD, formal verification, and architectural minimalism.
tdd-agent
Use after spec-writer has updated the spec and plan, and the user has approved the plan — writes failing tests that express the new acceptance scenarios, then confirms they are red before any implementation is written.
backend-evaluator
Backend QA evaluator. Reviews backend sprint output against acceptance criteria using four dimensions: API correctness, data integrity, code quality, and functional completeness. Runs tests and exercises APIs directly. Use after a backend generator sprint completes.
mock
API mocking — mock server design, contract testing, API simulation for development.