Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add neurawork-git/n8n-autopilot/plugin install 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/feedback)<a href="https://agentmods.dev/skills/neurawork-git/n8n-autopilot/feedback"><img src="https://agentmods.dev/badge/skills/neurawork-git/n8n-autopilot/feedback/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/feedback"><img src="https://agentmods.dev/badge/skills/neurawork-git/n8n-autopilot/feedback.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 | $0.01972 |
| Opus 5 | $0.00041 | $0.00986 |
| Sonnet 5 | $0.00016 | $0.00394 |
| Haiku 4.5 | $0.00008 | $0.00197 |
Grade A, and why
feedback scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Read, Grep, Glob, Bash(bash:*), Bash(node:*), Bash(curl:*) How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autopilot Feedback — Review, Redact, Push
The plugin learns from real usage. This skill reviews a session, removes anything
data-protected, and pushes the distilled learnings centrally so the same friction does not recur
across customers. Local stores live in the consumer repo under .n8n-autopilot/feedback/
(gitignored): events.ndjson (auto-captured signal counts from the SessionEnd hook) +
process.ndjson (review/interview output). The deterministic PII gate lives in
scripts/redact-check.js.
Parse $ARGUMENTS:
- empty /
review→ Review & push (default, the one-shot) interview→ short manual Q&A onlyshow→ list pending recordssync→ push existing pending records (re-runs the PII gate)
PII is non-negotiable. Consumer repos contain customer data. Everything that leaves the machine is (1) LLM-redacted to neutral insights and (2) passed through a deterministic allowlist gate (
redact-check.js) that BLOCKS emails, paths, URLs, long digit runs, tokens, and configured customer names. Counts + repo basename only; never transcript text or workflow content.
Review & push (default)
1. Resolve the session transcript
node "$CLAUDE_PLUGIN_ROOT/skills/feedback/scripts/latest-transcript.js" --workspace .
Use the printed path. (If it errors — no transcript — fall back to reviewing events.ndjson only.)
2. Gather auto-captured signals
Read .n8n-autopilot/feedback/events.ndjson — these are the SessionEnd hook's NON-PII friction
counts (the 11 operational classes + memory_oom + continue_on_fail). Summarize the totals.
3. Measure file-level design quality (accurate — read the actual workflows)
These design anti-patterns are NOT in the transcript counts; measure them from the real files.
Use Grep/Read over workflows/**/*.workflow.ts:
- Code-overuse (D1) — count
n8n-nodes-base.codevs nativeif/switch/filter. Flag Code nodes that only branch or remap (a native node would do it). Report the ratio. - Missing descriptions (D4) —
@workflow({...})without adescription; key nodes without notes. - Overlapping nodes (D5) — node
positionpairs within ~80px on both axes (unreadable canvas). - (Memory/OOM + continueOnFail already come from step 2's signals.)
What ships with it
5 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.
- 9d ago First seen · 160 lines · 81 tokens per session scan A 266593fbf350
feedback is a skill published in the GitHub repository neurawork-git/n8n-autopilot (18 stars, last pushed 1mo ago), licensed MIT. It adds 81 tokens to every session and 1,972 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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-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-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-error-handling
Wire n8n error handling so failures are loud, structured, and recoverable. Use when building any webhook/API workflow, a scheduled or unattended workflow, or any path where a silent failure would drop user-visible work — and whenever the user mentions error handling, onError, continueErrorOutput, error…
n8n-expression-syntax
Validate n8n expression syntax and fix common errors. Use when writing n8n expressions, using {{}} syntax, accessing $json/$node variables, troubleshooting expression errors, mapping data between nodes, or referencing webhook data in workflows. Use this skill whenever configuring node fields that reference data from…
n8n-node-configuration
Operation-aware node configuration guidance. Use when configuring nodes, understanding property dependencies, determining required fields, choosing between getnode detail levels, or learning common configuration patterns by node type. Always use this skill when setting up node parameters — it explains which fields are…
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…