sn-app-template
CLAUDE.md1 starsChanged 23 days agoMITView on GitHub
- Project skills live in .claude/skills/ (mirrored from .agents/skills/ by npm run sync:skills; edit the .agents/skills/ copy). Use add-table to add a table end to end and deploy-and-verify to deploy and test. - ServiceNow's official SDK skill is a plugin: /plugin install servicenow-sdk@claude-plugins-official. It teaches the npx now-sdk explain workflow that AGENTS.md relies on. - Optional instance access through MCP: copy .mcp.json.example to .mcp.json (gitignored) and export the SERVICENOW_* variables it references. Keep it read-only unless a task needs writes.…
In this repository5 other files it gives its agents.
- AGENTS.mdAGENTS.md
- add-tableSkill
- deploy-and-verifySkill
- add-tableSkill
- deploy-and-verifySkill
The file
Files
@AGENTS.md
Claude Code notes
- Project skills live in
.claude/skills/(mirrored from.agents/skills/bynpm run sync:skills; edit the.agents/skills/copy). Useadd-tableto add a table end to end anddeploy-and-verifyto deploy and test. - ServiceNow's official SDK skill is a plugin:
/plugin install servicenow-sdk@claude-plugins-official. It teaches thenpx now-sdk explainworkflow thatAGENTS.mdrelies on. - Optional instance access through MCP: copy
.mcp.json.exampleto.mcp.json(gitignored) and export theSERVICENOW_*variables it references. Keep it read-only unless a task needs writes. - Personal notes (instance names, local doc caches) go in
CLAUDE.local.md, which is gitignored.
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.

