Zum Inhalt springen
TakoAPI
Zurück zu den Skills

safety-checks

von leegitw

AI & LLMs
459Downloadzahlen laut clawskills.sh
1Aufrufe
0 LikesMelde dich an, um diesen Skill zu liken
—Noch nicht bewertet
Deine Bewertung

Kurzbeschreibung

Verify before you trust — model pinning, fallbacks, and runtime safety validation.

Beschreibung

Was dieser Skill macht

Runtime safety verification suite that consolidates model version pinning, fallback chain validation, cache staleness detection, and cross-session state checks. All operations are local file and metadata reads with no external API calls or data transmission. Consolidates four separate skills into a single aliased command.

Replaces four separate skill invocations with a single aliased suite that integrates directly with HEARTBEAT for automated periodic verification.

Wann du ihn einsetzt

  • Catching model version drift before a scheduled agent run
  • Verifying fallback config entries exist after modifying agent settings
  • Clearing stale cache entries during periodic workspace maintenance
  • Detecting orphaned lock files left by a previously crashed session
  • Running automated pre-flight safety checks on every session start via HEARTBEAT

Beispiel-Workflow

EINGABE

User asks: run a full safety check before starting the agent workflow

AGENT
  1. 1

    Run /sc model to compare active model version string against the pinned value in config

  2. 2

    Run /sc fallback to confirm fallback chain entries are declared in safety-checks.yaml

  3. 3

    Run /sc cache to identify cache entries older than the configured TTL

  4. 4

    Run /sc session to check for stale lock files or orphaned temp artifacts in output/safety/

AUSGABE

Four-check report with pass/warn/fail status per check; results written to output/safety/ logs

Installation

clawhub install leegitw/safety-checks

Führe den CLI-Befehl aus oder füge den Prompt in Claude Code, Cursor, Codex oder deinen Coding-Agenten ein.

Links