skill-listing-reset-on-real-skill-changes-38e522 — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited skill-listing-reset-on-real-skill-changes-38e522 (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Domain: command-surfaces Trigger: Apply when a system tracks which skills have already been announced and must decide when that sent-state should be cleared. Source Pattern: Distilled from reviewed command-surface and listing-control patterns.
Tie announcement-state resets to real changes in the underlying skill inventory, such as plugin reloads or skill file changes on disk. Do not clear the sent-state for compaction, transcript recovery, or other conversation-level churn, because that would force expensive re-injections of essentially unchanged listings. This keeps listing deltas meaningful and avoids paying thousands of tokens to restate the same inventory after every context-management event.
If a desktop agent reloads plugins and the available skill set changes, clear the sent-skill tracking map so the next listing can announce the new tools. If the conversation merely compacts or rehydrates from transcript, leave the sent-state alone so the agent does not spend tokens repeating an unchanged listing.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.