unfinished-threads — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited unfinished-threads (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.
L2 skill that filters to summaries matching:
thinking_stage IN ('exploring', 'crystallizing')importance IN ('breakthrough', 'significant') (or as configured)open_questions non-null and non-empty and not "none identified"Orders by importance DESC, then msg_count DESC. Max 25 rows.
Distinct from L3 open-threads because this is single-summary granularity — one row per conversation — not domain-aggregated.
domain: str | None
importance: "breakthrough" | "significant" = "significant"## 🧵 Unfinished Threads {domain or 'across all domains'}
**Importance filter**: {importance}+ · **Results**: N
💎 **{title}** · {domain_primary} · {stage}
[conv_id · date] · {msg_count} msgs
> {summary 200ch}
Open questions (max 3 shown):
- {q 200ch}
- {q 200ch}open-threads)dormant-contexts)~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.