prevent-continuation-stop-hook-contract-d6e5b8 — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited prevent-continuation-stop-hook-contract-d6e5b8 (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.
Domain: tool-orchestration Trigger: Apply when post-response hooks may decide that the query loop must stop, but the caller still needs a structured non-exception contract. Source Pattern: Distilled from reviewed tool-loop and result-shaping patterns.
Represent stop-hook outcomes with a compact return contract instead of control-flow exceptions. Separate hard blocking errors from the boolean that says continuation should stop, and let the loop interpret that result after hooks, teammate callbacks, and summary messages have all been emitted. This keeps hook orchestration observable and composable while still allowing hooks to end the turn decisively.
{ blockingErrors, preventContinuation } rather than throwing for normal stop decisions.If a stop hook determines that a teammate should pause after reaching idle state, emit the relevant hook summary and return preventContinuation: true. The query loop can then stop cleanly without mistaking that decision for a crash.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.