Saltar al contenido
TakoAPI
Volver a skills

safety-checks

por leegitw

AI & LLMs
459Descargas según clawskills.sh
1Vistas
0 me gustaInicia sesión para dar me gusta a esta skill
—Aún sin valoraciones
Tu valoración

Resumen

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

Descripción

Qué hace esta skill

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.

Cuándo usarla

  • 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

Flujo de trabajo de ejemplo

ENTRADA

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

AGENTE
  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/

SALIDA

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

Instalación

clawhub install leegitw/safety-checks

Ejecuta el comando de la CLI o pega el prompt en Claude Code, Cursor, Codex o el agente de programación que uses.

Enlaces