Preview and permanently delete a NeatContext context while preserving any externally linked knowledge folder. Use only when the user explicitly invokes this skill or clearly asks to delete a context.
Scanned 8/31/2026
Install to Claude Code
Skills Directorynpx -y skills add XTSoftwareLabs/neatcontext-plugins --skill delete --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Delete?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/xtsoftwarelabs-delete)More formats (shields.io, HTML) on the badges page.
---
name: delete
description: Preview and permanently delete a NeatContext context while preserving any externally linked knowledge folder. Use only when the user explicitly invokes this skill or clearly asks to delete a context.
---
# Delete context
Resolve `<plugin-root>` as two directories above the directory containing this file.
List contexts first:
```text
node "<plugin-root>/src/codex/neatcontext-cli.mjs" list
```
If the requested name is missing or does not resolve to exactly one context, show the list and ask which one. Never guess.
Preview the deletion without changing anything:
```text
node "<plugin-root>/src/codex/neatcontext-cli.mjs" delete "<exact-name>"
```
Relay exactly what the preview says will be removed or retained and wait for explicit confirmation.
After confirmation, run:
```text
node "<plugin-root>/src/codex/neatcontext-cli.mjs" delete "<exact-name>" --yes
```
Relay the result. If it was connected, say that this thread is no longer grounded and suggest `$neatcontext:use`.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
