Token Guard Model Switch
Security checks across static analysis, malware telemetry, and agentic risk
Overview
The skill's files, instructions, and requirements are consistent with a local token-monitoring / model-switch helper and do not ask for unrelated credentials or networked installs.
This skill appears coherent and lightweight: it uses a small local Node script to compute token ratios and instructs the agent to switch models when thresholds are hit. Before installing: (1) confirm you have node available and that the agent can run local scripts; (2) inspect scripts/monitor.js (it’s short and only prints a status) — there are no hidden network calls or credential reads; (3) ensure the referenced Windows path matches your environment or update the instructions to use a cross-platform path; (4) verify your agent has the session-modification capability (sessions.patch or equivalent) and that you’re comfortable with automated model switching to local runtimes (e.g., Ollama) if you use that option.
Static analysis
Static analysis findings are pending for this release.
VirusTotal
VirusTotal findings are pending for this skill version.
Risk analysis
No visible risk-analysis findings were reported for this release.