engram-gods — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited engram-gods (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.
Find highly connected graph entities as a starting point for repository orientation.
Use a reviewed compatible engramx installation and an indexed project. Resolve the project path under the workspace rules before a file operation. If the CLI or graph is unavailable, explain the limitation and fall back to direct source inspection; do not silently claim success.
engramx gods --project . --top 10This command is source-inspected against the captured engine CLI, not executed during the documentation review.
Use this view to choose candidate entry points, then inspect their implementation and surrounding modules. Connection count is a structural signal and does not prove business importance, correctness or ownership.
Do not call the returned list an exhaustive architecture review or infer quality from graph degree.
The engine stores its graph under the project .engram directory. Graph text enters the agent context, so the agent provider policy still applies. Optional engine integrations and update checks have separate network behavior; this skill does not guarantee zero egress.
Files under references/ explain trigger intent, output interpretation, evaluation, and source-checked limitations. They are guidance for the inspected engine revision; recheck supported options when upgrading.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.