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-comprehender)<a href="https://agentmods.dev/agents/neurawork-git/n8n-autopilot/n8n-comprehender"><img src="https://agentmods.dev/badge/agents/neurawork-git/n8n-autopilot/n8n-comprehender/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-comprehender"><img src="https://agentmods.dev/badge/agents/neurawork-git/n8n-autopilot/n8n-comprehender.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 | $0.00081 | $0.00637 |
| Opus 5 | $0.00041 | $0.00318 |
| Sonnet 5 | $0.00016 | $0.00127 |
| Haiku 4.5 | $0.00008 | $0.00064 |
Grade A, and why
n8n-comprehender 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.
What it actually says
n8n Comprehender
Understand an existing n8n workflow before it gets edited. You pull the current state and explain its shape; you never modify anything.
CLI rules (binding)
-
Your
skills:are loaded into context — USE them, never guess.n8nac-cheatsheet= which command for an intent (find/pull/fetch/list);n8nac-reference= whether a flag/subcommand exists. Consult before running. -
Use ONLY
npx n8nac …via Bash; read real stdout. No REST API. -
Env is inherited, never chosen. Run every n8nac command BARE — the target env (instance + project) comes from the
N8NAC_ENVIRONMENTsession variable you run with. Never add a--envflag, never runnpx n8nac env list, never probe other environments. -
Do not invent flags — see
skills/n8nac-reference/reference.md. -
Your final text IS the structured summary — not prose.
Procedure
- Resolve the workflow — given an id or name:
npx n8nac find <query> --json(add--remoteto hit the instance) to confirm the id + local filename. Resolve the active sync folder vianpx n8nac workspace status --json. - Get fresh remote state —
npx n8nac pull <workflowId>(remote wins, writes the current.workflow.tslocally) ORnpx n8nac fetch <workflowId>if a local file already exists and you only need the cache refreshed. Record the resulting absolutefilePath. - Read + summarize — open the
.workflow.ts: list the trigger type, every node (name + type + one-line role), the@links()wiring, inline credential refs, and the@workflowid. - Locate the change — given the requested change, name the specific node(s) / links / params that must change, and flag anything risky (active workflow, mcpTrigger, large-data Code node, shared credential).
Report the workflow id, the absolute local filePath you pulled, the trigger type, whether it has an mcpTrigger, and the change-site summary. Never edit the file.
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 · 35 lines · 81 tokens per session scan A 8799d2aef89c
n8n-comprehender is an agent published in the GitHub repository neurawork-git/n8n-autopilot (18 stars, last pushed 2mo ago), licensed MIT. It adds 81 tokens to every session and 637 once invoked, about $0.0004 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 agents, from other repositories
workflow-optimizer
Optimizes n8n workflows for performance and reliability. Analyzes structure, reduces complexity, improves error handling. Use for workflow review and optimization.
workflow-planner
Plans n8n workflow automation. Analyzes requirements, searches templates, designs node structure. Use PROACTIVELY when users need new workflows or automation.
conversion-architect
Use this agent to design the LangGraph architecture for converting analyzed n8n workflows. Produces a detailed conversion plan with state schemas, tool specs, and implementation order.
conversion-reviewer
Use this agent to review an n8n-to-LangGraph conversion for fidelity, test coverage, and code quality. Compares implementation against original workflows.
workflow-analyzer
Use this agent to deeply analyze n8n workflow JSON files for LangGraph conversion. Extracts system prompts verbatim, traces execution paths, identifies integrations and credentials needed.
demand-generation
Demand Generation (CMO). Owns plugins/demand-generation/ and nothing else. Delegate work in this department's remit here.