n8n-mode
Skill18 starsChanged 44 days agoMITView on GitHub
Switch the per-session n8n mode on, off, or show its status. While it is off, n8n-autopilot stays out of the session (no SessionStart probes, no feedback Stop gate, no feedback capture) — the safety gates on n8nac commands always apply. Use when the user says "n8n mode on", "n8n-Modus an", "start n8n work", "I want to work on n8n workflows now", "turn n8n off", "why does n8n-autopilot fire here", or before n8n work in a project monorepo.
In this repository25 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- build-stack-v2Skill
- build-workflowSkill
- build-workflow-v2Skill
- check-mcpsSkill
- data-tablesSkill
- deploySkill
- feedbackSkill
- find-credentialSkill
- find-projectSkill
- init-repoSkill
- inventorySkill
- mirror-syncSkill
- n8nac-cheatsheetSkill
- n8nac-referenceSkill
- n8n-code-javascriptSkill
- n8n-code-pythonSkill
- n8n-orchestration-patternsSkill
- n8n-structured-extractionSkill
- plugin-testingSkill
- pull-schemasSkill
- session-envSkill
- stack-intakeSkill
- sync-credentialsSkill
- test-manualSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 11
Run, with the argument the user gave (default on):
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
n8n mode — n8n-autopilot only where n8n work happens
Run, with the argument the user gave (default on):
bash "${CLAUDE_PLUGIN_ROOT}/scripts/n8n-mode.sh" <on|off|status> "${CLAUDE_SESSION_ID}"on runs the probes against the instance and takes about a minute — give the Bash call a
5-minute timeout. Show the output. With on it also runs the SessionStart probes once — follow any
AUTOPILOT_ACTION_REQUIRED: line exactly as CLAUDE.md "Auto-Reactions on SessionStart" says.
How the mode works
| Repo / session | Probes at session start | Feedback Stop gate + capture | Safety gates on n8nac commands |
| always-on repo | yes | yes | yes |
| other repo, mode off | no (one hint line if an n8n workspace sits in a subfolder) | no | yes |
other repo, mode on (this skill or first n8nac command) | once, when switched on via this skill | yes | yes |
Always-on (the project dir is an n8n workspace) — any of:
workflows/in the project root holding*.workflow.ts— a dedicated n8n repo, or a monorepo'sn8n/folder opened as its own projectn8nac-config.jsonin the project rootN8N_AUTOPILOT_MODE=alwaysin theenvblock of.claude/settings.json.n8n-autopilot/modecontaining the linealways
A session in a monorepo root (workflows under n8n/workflows/) starts with the mode off. When this
skill switches it on there, it runs the probes inside the n8n/ folder and takes
N8NAC_ENVIRONMENT from n8n/.claude/settings.json if the session has none — the session's own
shell still lacks it, so pass --env <name> or prefix N8NAC_ENVIRONMENT=<name> on n8nac calls.
N8N_AUTOPILOT_MODE=off keeps the mode off, even after an n8nac command.
The first n8nac command of a session switches the mode on automatically (silent, no probes). Run
this skill instead when you want the setup/drift probes before you start.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

