MCP HubMCP Hub
Retour aux compétences

agent-usage-optimizer-step-1-read-and-validate-quota-cache

vamseeachanta
Mis à jour Today
50 vues
3
2
3
Voir sur GitHub
Autregeneral

À propos

Cette compétence lit et valide un fichier de quota en cache pour vérifier la disponibilité d'utilisation de l'API Claude. Elle vérifie que le cache existe et qu'il a moins d'une heure, en fournissant des avertissements s'il est obsolète ou manquant. Utilisez cette étape initiale dans le routage des agents pour déterminer si les modèles Claude sont disponibles avant de poursuivre.

Installation rapide

Claude Code

Recommandé
Principal
npx skills add vamseeachanta/workspace-hub
Commande PluginAlternatif
/plugin add https://github.com/vamseeachanta/workspace-hub
Git CloneAlternatif
git clone https://github.com/vamseeachanta/workspace-hub.git ~/.claude/skills/agent-usage-optimizer-step-1-read-and-validate-quota-cache

Copiez et collez cette commande dans Claude Code pour installer cette compétence

Documentation

Step 1 — Read and Validate Quota Cache

Step 1 — Read and Validate Quota Cache

QUOTA_FILE="$HOME/.cache/agent-quota.json"

# Check cache exists and is fresh (< 1 hour old)
if [[ ! -f "$QUOTA_FILE" ]]; then
  echo "WARN: quota cache not found at $QUOTA_FILE"
  echo "Run: bash scripts/monitoring/query-quota.sh"
  echo "Falling back to default routing rules."
  CACHE_FRESH=false
else
  CACHE_AGE_SECS=$(( $(date +%s) - $(date -r "$QUOTA_FILE" +%s) ))
  if [[ $CACHE_AGE_SECS -gt 3600 ]]; then
    echo "WARN: quota cache is $(( CACHE_AGE_SECS / 60 ))m old — consider refreshing"
    CACHE_FRESH=false
  else
    CACHE_FRESH=true
  fi
fi

# Parse quota values (requires jq)
CLAUDE_PCT=$(jq -r '.agents[] | select(.provider=="claude") | .pct_remaining' "$QUOTA_FILE" 2>/dev/null || echo 100)
CODEX_PCT=$(jq  -r '.agents[] | select(.provider=="codex")  | .pct_remaining' "$QUOTA_FILE" 2>/dev/null || echo 100)
GEMINI_PCT=$(jq -r '.agents[] | select(.provider=="gemini") | .pct_remaining' "$QUOTA_FILE" 2>/dev/null || echo 100)
CACHE_TS=$(jq  -r '.timestamp' "$QUOTA_FILE" 2>/dev/null || echo "unknown")

Dépôt GitHub

vamseeachanta/workspace-hub
Chemin: .claude/skills/ai/agent-usage-optimizer/step-1-read-and-validate-quota-cache

Compétences associées

algorithmic-art

Méta

This Claude Skill creates original algorithmic art using p5.js with seeded randomness and interactive parameters. It generates .md files for algorithmic philosophies, plus .html and .js files for interactive generative art implementations. Use it when developers need to create flow fields, particle systems, or other computational art while avoiding copyright issues.

Voir la compétence

subagent-driven-development

Développement

This skill executes implementation plans by dispatching a fresh subagent for each independent task, with code review between tasks. It enables fast iteration while maintaining quality gates through this review process. Use it when working on mostly independent tasks within the same session to ensure continuous progress with built-in quality checks.

Voir la compétence

executing-plans

Design

Use the executing-plans skill when you have a complete implementation plan to execute in controlled batches with review checkpoints. It loads and critically reviews the plan, then executes tasks in small batches (default 3 tasks) while reporting progress between each batch for architect review. This ensures systematic implementation with built-in quality control checkpoints.

Voir la compétence

cost-optimization

Autre

This Claude Skill helps developers optimize cloud costs through resource rightsizing, tagging strategies, and spending analysis. It provides a framework for reducing cloud expenses and implementing cost governance across AWS, Azure, and GCP. Use it when you need to analyze infrastructure costs, right-size resources, or meet budget constraints.

Voir la compétence