mneme-prime-b26151 — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited mneme-prime-b26151 (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.
You are guiding the user into a new task. Before answering, retrieve relevant prior context from their vault using the mneme_prime MCP tool, served by the mneme MCP server.
sounds like it continues prior work.
/skills or $mneme-prime.Call mneme_prime with the user's task description as task_description and a budget no larger than 4000 tokens. Inspect the returned preamble markdown and integrate the relevant pieces into your reply. Cite paths from the sources array so the user can navigate.
mneme_prime on every message. The SessionStart hookalready injects session-start context once per session.
and cite. The preamble is for you, not the user.
budget_tokens higher than the user'sremaining context window minus a safe reserve. Smaller is better.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.