hyv-inspect-hidden-text

SkillDev tools

Inspect hidden text controls with a non-mutating policy report.

Available today. Use it from your connected AI after setup.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the hyv-inspect-hidden-text skill

What this skill tells your AI

The instructions your AI receives, as published by shashank-sn/holdyourvoice in skills/hyv-inspect-hidden-text/SKILL.md and read by ahel’s review.

Inspect hidden text controls with a non-mutating policy report. Findings are not watermark verdicts. An optional policy.json restricts which controls are reported.

Usage

hyv inspect-hidden-text draft.md [policy.json]

Behavior

  • Deterministic and local-first: this command never calls a provider and never sends drafts, samples, profiles, or telemetry to a service.
  • Commands that write use an explicit output path. Confirm that path before running the command.
  • This agent describes how to invoke the command and what it returns. It does not change command behavior or exit codes.

Handoff

Run hyv inspect-hidden-text directly to execute the operation. Follow-on agents: hyv-apply-hidden-text-policy, hyv-final-check.

Signals

GitHub stars
32
Last commit
Sep 2026
Advanced
Item type
skill
Key
hyv-inspect-hidden-text
Source
github.com/shashank-sn/holdyourvoice