mental-model — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited mental-model (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 working on this codebase, first check for mental-model.md in the project root.
Read it to understand the codebase architecture, patterns, conventions, and relationships before making changes, when exploring unfamiliar parts of the code, or debugging failed tests or unexpected behavior.
Update it whenever you discover something new — from running tests, hitting unexpected behavior, or exploring unfamiliar parts of the code.
Ask the user if they'd like you to create one. If confirmed:
Create a new file named mental-model.md at the repo root, that builds and maintains a full mental model of the codebase.
Scan the entire codebase and document how the system works end-to-end (architecture, key modules, data flow, relationships, testing approach, Docker/setup, etc).
Treat this as a living document. Update it whenever you learn something new from running tests or hitting unexpected behavior.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.