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 Impertio-Studio/n8n-Claude-Skill-Package --skill n8n-syntax-workflow-jsongit clone --depth 1 https://github.com/Impertio-Studio/n8n-Claude-Skill-PackageWrote 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/impertio-studio/n8n-claude-skill-package/n8n-syntax-workflow-json)<a href="https://agentmods.dev/skills/impertio-studio/n8n-claude-skill-package/n8n-syntax-workflow-json"><img src="https://agentmods.dev/badge/skills/impertio-studio/n8n-claude-skill-package/n8n-syntax-workflow-json/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/impertio-studio/n8n-claude-skill-package/n8n-syntax-workflow-json"><img src="https://agentmods.dev/badge/skills/impertio-studio/n8n-claude-skill-package/n8n-syntax-workflow-json.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 | $0.00133 | $0.02550 |
| Opus 5 | $0.00067 | $0.01275 |
| Sonnet 5 | $0.00027 | $0.00510 |
| Haiku 4.5 | $0.00013 | $0.00255 |
Grade A, and why
n8n-syntax-workflow-json 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 10d 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 — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
n8n-syntax-workflow-json
Quick Reference
Workflow JSON Top-Level Structure (IWorkflowBase)
| Field | Type | Required | Purpose |
|---|---|---|---|
id |
string |
YES | Unique workflow identifier |
name |
string |
YES | Human-readable workflow name |
active |
boolean |
YES | Whether workflow listens for triggers |
isArchived |
boolean |
YES | Whether workflow is archived |
nodes |
INode[] |
YES | Array of all nodes in the workflow |
connections |
IConnections |
YES | Connection map between nodes |
settings |
IWorkflowSettings |
NO | Workflow-level configuration |
staticData |
IDataObject |
NO | Persistent data (polling state, etc.) |
pinData |
IPinData |
NO | Pinned test data for manual execution |
description |
string | null |
NO | Workflow description |
versionId |
string |
NO | Version identifier |
meta |
WorkflowFEMeta |
NO | Frontend metadata (template ID, etc.) |
INode Fields
| Field | Type | Required | Purpose |
|---|---|---|---|
id |
string |
YES | Unique node ID (UUID format) |
name |
string |
YES | Display name (MUST be unique in workflow) |
type |
string |
YES | Node type (e.g., n8n-nodes-base.httpRequest) |
typeVersion |
number |
YES | Node version number |
position |
[number, number] |
YES | Canvas position [x, y] |
parameters |
INodeParameters |
YES | Node parameter values |
credentials |
INodeCredentials |
NO | Credential references |
disabled |
boolean |
NO | Whether node is disabled |
notes |
string |
NO | User-visible notes |
notesInFlow |
boolean |
NO | Show notes on canvas |
webhookId |
string |
NO | Webhook ID (webhook nodes only) |
retryOnFail |
boolean |
NO | Retry on error |
maxTries |
number |
NO | Max retry attempts |
waitBetweenTries |
number |
NO | Milliseconds between retries |
alwaysOutputData |
boolean |
NO | Output empty item if no data |
executeOnce |
boolean |
NO | Execute only for first item |
onError |
OnError |
NO | Error behavior strategy |
continueOnFail |
boolean |
NO | Continue workflow on error |
What ships with it
3 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.
- 10d ago First seen · 272 lines · 133 tokens per session scan A b69ea553ff76
n8n-syntax-workflow-json is a skill published in the GitHub repository Impertio-Studio/n8n-Claude-Skill-Package (3 stars, last pushed 2mo ago), licensed MIT. It adds 133 tokens to every session and 2,550 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
qgis-agents-analysis-orchestrator
Use when planning a spatial analysis workflow, choosing between analysis approaches, or chaining multiple operations. Prevents wrong analysis method selection and suboptimal workflow ordering. Covers vector vs raster decision trees, processing algorithm selection, workflow chaining, CRS/format guidance, and MCP server…
qgis-errors-data-loading
Use when diagnosing data loading failures, invalid layers, or provider connection errors. Prevents silent failures from unchecked layer validity and incorrect URI formats. Covers invalid layer detection, URI format errors, encoding issues, GeoPackage locking, connection failures, and performance. Keywords: invalid…
qgis-errors-projections
Use when diagnosing CRS/projection errors, coordinate mismatches, or datum transformation issues. Prevents silent data corruption from wrong CRS assignment and coordinate order confusion. Covers wrong EPSG selection, lat/lon vs lon/lat, datum warnings, on-the-fly reprojection pitfalls, and fix patterns. Keywords: CRS…
qgis-agents-map-generator
Use when generating complete maps from data: loading, styling, composing layouts, and exporting. Prevents poor cartographic choices and empty map exports. Covers the full map pipeline: data loading, symbology selection, labeling, layout composition, atlas generation, and export. Keywords: map generation, create map…
qgis-core-architecture
Use when creating QGIS projects, understanding PyQGIS architecture, or reasoning about the QGIS data model. Prevents mixing standalone script initialization with plugin context, and threading violations. Covers Qt-based architecture, 5 core modules, project lifecycle, layer model, provider system, and QGIS 4.0 Qt6…
qgis-impl-3d-visualization
Use when creating 3D map views, configuring terrain, or rendering vector/point cloud data in 3D. Prevents performance issues from unoptimized point cloud rendering and incorrect terrain configuration. Covers Qgs3DMapSettings, terrain providers, 3D symbols, materials, camera/lights, and layout integration. Keywords: 3D…