Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/psd401/psd-claude-pluginsnpx agentmods add skills/psd401/psd-claude-plugins/n8n-managerWrote 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/psd401/psd-claude-plugins/n8n-manager)<a href="https://agentmods.dev/skills/psd401/psd-claude-plugins/n8n-manager"><img src="https://agentmods.dev/badge/skills/psd401/psd-claude-plugins/n8n-manager.svg" alt="Measured on agentmods" 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 | $0.00096 | $0.04497 |
| Opus 5 | $0.00048 | $0.02249 |
| Sonnet 5 | $0.00019 | $0.00899 |
| Haiku 4.5 | $0.00010 | $0.00450 |
Grade A, and why
n8n-manager 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 6d 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.
- **n8n masks Documenso 400 errors as ECONNREFUSED** — when `POST /api/v2/envelope/create` returns HTTP 400 with a JSON validation error (e.g. missing `type: 'DOCUMENT'`), the n8n HTTP Request node with multipart-form-da How it starts
The opening of the file, as written. The whole thing — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.
n8n Manager
Configuration
- Server: Read from
N8N_HOSTenvironment variable (never hardcoded) - API Auth:
X-N8N-API-KEYheader viaN8N_API_KEYenv var - Instance MCP: Native n8n MCP at
N8N_HOST/mcp-server/http(bearer token fromN8N_MCP_TOKEN) - Docs MCP: czlonkowski/n8n-mcp for node documentation and templates
- Version: n8n Community Edition v2.14.x
- Scripts:
plugins/psd-productivity/skills/n8n-manager/scripts/
All scripts use bun and read credentials from secrets.js (env vars → Geoffrey .env).
Community Edition Limitations
PSD runs n8n Community Edition. These features are not available:
- No Settings → Variables — environment variables are enterprise/pro only. All config values (API keys, URLs, folder IDs) must be hardcoded directly in workflow node parameters.
- No instance-level error workflow — must set
errorWorkflowin each workflow'ssettingsobject individually. - Credentials API returns 403 — credential listing/reading is restricted. Get credential IDs from the user via the n8n UI.
- No source control / Git integration — workflows must be managed via API or UI exports.
Command Reference
Workflow Management
| Command | Script | Description |
|---|---|---|
/n8n status |
bun health_check.js |
Server health, version, workflow count |
/n8n list |
bun list_workflows.js |
List all workflows |
/n8n list '{"active":true}' |
bun list_workflows.js '{"active":true}' |
Filter by status |
/n8n list '{"tag":"psd-production"}' |
bun list_workflows.js '{"tag":"psd-production"}' |
Filter by tag |
/n8n show <id> |
bun get_workflow.js <id> |
Get full workflow JSON |
/n8n activate <id> |
bun activate_workflow.js <id> |
Activate workflow |
/n8n deactivate <id> |
bun deactivate_workflow.js <id> |
Deactivate workflow |
/n8n delete <id> |
bun delete_workflow.js <id> |
Delete workflow (confirm first) |
Workflow Builder
What ships with it
33 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.
- references/documenso-n8n-patterns.md 12 KB
- references/n8n-node-catalog.md 19 KB
- references/n8n-workflow-json-spec.md 7.1 KB
- references/psd-integration-map.md 5.8 KB
- references/psd-workflow-templates.md 8.5 KB
- scripts/activate_workflow.js 837 B runs code
- scripts/create_credential.js 1.2 KB runs code
- scripts/create_tag.js 623 B runs code
- scripts/create_variable.js 693 B runs code
- scripts/create_workflow.js 1.4 KB runs code
- scripts/deactivate_workflow.js 849 B runs code
- scripts/delete_workflow.js 1.5 KB runs code
- scripts/deploy_workflow.js 2.6 KB runs code
- scripts/get_credential_schema.js 861 B runs code
- scripts/get_execution.js 1.2 KB runs code
- scripts/get_workflow.js 755 B runs code
- scripts/health_check.js 904 B runs code
- scripts/list_credentials.js 706 B runs code
- scripts/list_executions.js 1.5 KB runs code
- scripts/list_folders.js 1.5 KB runs code
- scripts/list_tags.js 590 B runs code
- scripts/list_variables.js 604 B runs code
- scripts/list_workflows.js 1.5 KB runs code
- scripts/manage_folders.js 9.8 KB runs code
- scripts/n8n_client.js 1.4 KB runs code
- scripts/n8n_mcp_client.js 3.4 KB runs code
- scripts/n8n-mcp-proxy.sh 1.6 KB runs code
- scripts/retry_execution.js 758 B runs code
- scripts/rotate_documenso_key.js 3.5 KB runs code
- scripts/run_audit.js 861 B runs code
- scripts/trigger_workflow.js 1.6 KB runs code
- scripts/update_workflow.js 1.4 KB runs code
- scripts/validate_workflow.js 4.5 KB runs code
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.
- 6d ago First seen · 274 lines · 96 tokens per session scan A 313961208e6a
n8n-manager is a skill published in the GitHub repository psd401/psd-claude-plugins (2 stars, last pushed 6d ago), licensed MIT. It adds 96 tokens to every session and 4,497 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
recipe-fullstack-implement
Orchestrate full-cycle implementation across backend and frontend layers.
news-search
Search current news for a topic, company, competitor, or hook and return dated, attributed articles. Uses the newsjack CLI and Medialyst REST API when available, tries direct Medialyst MCP if the CLI is missing, and falls back to host web/browser search with explicit caveats only when neither cloud path is available.
notion
Notion workspace integration for searching pages, managing databases, creating postmortems, and exporting RCA findings.
output-error-direct-io
Fix direct I/O in Output SDK workflow functions. Use when workflow hangs, returns undefined, shows "workflow must be deterministic" errors, or when HTTP/API calls are made directly in workflow code.
output-dev-workflow-cost
Calculate and display the cost of an Output SDK workflow execution run. Use when checking LLM token costs, API service costs, or total spend for a specific workflow run.
remote-offload
Instructions for sending heavy jobs such as scraping, video encoding, builds, or bulk API collection from a low-memory laptop to another computer over SSH, a secure remote connection.