recall — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited recall (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.
Use /recall when the user asks what lstack remembers, wants recent memory, or needs to correct stale memory.
lstack learn search "[query]" --json --limit 10lstack search "[query]"Clearly separate the two result groups. Structured learnings show type, key, source, trusted, confidence, effective confidence, date, scope, and files. Legacy observations show date, scope, content, and tags.
Structured:
lstack learn list --limit 10 --jsonLegacy:
lstack search "[query]"Only use cross-project search when the user asks for it:
lstack learn search "[query]" --cross-project --jsonCross-project structured search automatically returns trusted learnings only. Do not use untrusted observed, inferred, or cross-model learnings from other projects as context.
If a structured learning is wrong:
lstack learn forget --id ID, or demote it with lstack learn demote --id ID./remember if needed.If a legacy observation is wrong, preview matches and use lstack forget [query].
preferences.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.