/

/ctx-doctor

1,777

Run context-mode diagnostics. Checks runtimes, hooks, FTS5, plugin registration, npm and marketplace versions. Trigger: /context-mode:ctx-doctor

Ask your Agent

Use this Skill: https://skilld.dev/gh/mksglu/context-mode/ctx-doctor

This session only. Nothing lands on disk.

SKILL.md

≈39 tokens always: the name and description. ≈209 when used: this file.

Run diagnostics and display results directly in the conversation.

Call the ctx_doctor MCP tool directly. It runs all checks server-side and returns a plain-text status report.
Display the results verbatim — they are already formatted with plain-text status prefixes: [OK] PASS, [FAIL] FAIL, [WARN] WARN. Renderer-safe (no markdown task-list syntax) for cross-client compatibility (e.g., Z.ai GLM).
Fallback (only if MCP tool call fails): Derive the plugin root from this skill's base directory (go up 2 levels — remove /skills/ctx-doctor), then run with Bash:
```
CLI="<PLUGIN_ROOT>/cli.bundle.mjs"; [ ! -f "$CLI" ] && CLI="<PLUGIN_ROOT>/build/cli.js"; node "$CLI" doctor
```
Re-display results verbatim with the same [OK]/[FAIL]/[WARN] prefixes.

1 warning17d4 checks · Risk MEDIUM

Gen Agent Trust Hub17d
The skill includes a fallback mechanism that executes a local Node.js script using a dynamically computed path. It also instructs the agent to display external tool output verbatim, creating a potential surface for indirect prompt injection.
Socket17d
No alerts
Snyk17d
Risk: LOW · No issues
Runlayer6mo
1/1 file flagged

Signed by skilld at eea5877. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 5 months ago