fai-remember — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited fai-remember (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.
Save and organize persistent notes for AI assistants across sessions.
/memories/
├── preferences.md # User coding style, tools, conventions
├── patterns.md # Reusable solutions to common problems
├── debugging.md # Past debugging insights
└── session/
├── current-task.md # Active task context
└── findings.md # Session-specific discoveries| Category | Examples |
|---|---|
| Preferences | "Always use Managed Identity, never connection strings" |
| Patterns | "Use circuit breaker for all external API calls" |
| Project context | "This repo uses FastAPI + Cosmos DB + AI Search" |
| Debugging | "Port 3000 conflict: kill serve process before restart" |
| Conventions | "Commit format: feat(scope): description" |
| Practice | Why |
|---|---|
| Keep entries concise | Memory is loaded into context — brief = efficient |
| Organize by topic | Separate files for preferences, patterns, debugging |
| Update, don't duplicate | Edit existing entries instead of adding new ones |
| Delete when obsolete | Remove outdated information |
| Session memory for temp | Use session/ for task-specific, non-persistent notes |
# preferences.md
- Use Python 3.11+ with type hints
- Prefer FastAPI over Flask for new APIs
- Always use DefaultAzureCredential, never hardcode keys
- Use ruff for linting (not flake8)
- Commit messages follow conventional commits
# debugging.md
- PowerShell here-strings corrupt markdown backticks — use Node.js for file gen
- Azure OpenAI 403: check MI role assignment, wait 5 min for propagation
- Next.js dev server holds 2-3GB RAM — use `npx serve out` for preview| Issue | Cause | Fix |
|---|---|---|
| Memory too large | Too many entries | Prune old/obsolete entries |
| Duplicate entries | Not checking existing | Read memory before writing |
| Wrong scope | Session note saved globally | Use session/ for temporary context |
| Stale information | Never updated | Review and update regularly |
| Practice | Rationale |
|---|---|
| Start simple, add complexity when needed | Avoid over-engineering |
| Automate repetitive tasks | Consistency and speed |
| Document decisions and tradeoffs | Future reference for the team |
| Validate with real data | Don't rely on synthetic tests alone |
| Review with peers | Fresh eyes catch blind spots |
| Iterate based on feedback | First version is never perfect |
fai-implementation-plan-generator — Planning and milestonesfai-review-and-refactor — Code review patternsfai-quality-playbook — Engineering quality standards~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.