compile-context — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited compile-context (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.
When the user asks to compile context or create a brief for a topic, call create_snapshot to synthesize a context brief from the vault.
If the user provided a topic or project name, use it. If not, ask:
"What topic or project should I compile context for?"
Derive a slug: lowercase, hyphens, no spaces (e.g. neonode, context-vault, klarhimmel-infra).
Call create_snapshot with:
topic: the topic name the user providedidentity_key: snapshot-<slug> (e.g. snapshot-context-vault)tags (optional): any relevant tags the user mentionskinds (optional): restrict to specific entry kinds if the user requests itThe tool handles retrieval, deduplication, LLM synthesis, and saving automatically.
After the tool returns, tell the user:
get_context(identity_key: "snapshot-<slug>")~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.