MCP App StoreMCP App Store
from bendrucker/claude10
Query and analyze Claude Code session history: session IDs, token usage, tool patterns, per-project stats and searchable past conversations via a DuckDB index.
This skill exposes a DuckDB-backed index of Claude Code JSONL session logs, letting agents run named queries and ad-hoc SQL to surface session-level stats (duration, tokens), tool usage patterns, recent activity, errors, sandbox bypasses, and searchable conversation content. It provides scripts and named queries for common reports and can refresh the index on demand.
Use this skill when the user asks about their Claude Code activity: retrieving session IDs, checking daily token consumption, finding past conversations, auditing tool usage or errors, or extracting sandbox bypass incidents. Do NOT use it for arbitrary codebase searches or non-session data.
Intended for Claude Code plugin hosts and agents that can run Bash and read local files; best suited to Claude Code environments with access to session JSONL logs and the plugin data directory.
Claude Code session introspection skill that builds a DuckDB index over ~/.claude/projects/**/*.jsonl files and provides 20+ parameterized named queries for searching, analyzing, and exporting session history. Exceptionally well-documented SKILL.md with detailed query catalog, cross-machine import workflow, and privacy egress controls. Scripts are TypeScript requiring Bun runtime and could not be executed by the auditor. Architecture follows skill spec with clean scripts/resources/references separation and versioned migration.
bunduckdb@duckdb/node-apicleyetableVery high quality skill. Minor security note: runQuery() interpolates param keys into SET VARIABLE statements, but keys come from controlled named-query definitions rather than arbitrary user input. Egress policy system (block_egress) is a thoughtful privacy feature for cross-machine imports.
Cost Tracker
Monitor agent session costs, set budget alerts, and get actionable token-spend optimizations to keep multi-session workflows within budget.
Shopify Store Audit
Structured, page-by-page audit of Shopify storefronts to find conversion blockers and prioritized fixes for copy, UX, trust signals, and checkout friction.
Canary — Post-Deploy Visual Monitor
Run a short post-deploy monitor that captures screenshots, checks console errors, and compares performance against baselines to detect regressions and page fail
Reppo — AgentMind Publisher
Publish creative content to Moltbook and mint posts as on-chain pods on Reppo.ai (Base) to earn $REPPO through human voting.
Monitoring Stack Deployer
Deploy and configure production-ready monitoring stacks (Prometheus, Grafana, Datadog) with collectors, dashboards, and alerting rules for Kubernetes, Docker, o
Cross-Project Analytics
Query local, privacy-safe cross-project analytics to report on agent, skill, hook, and team performance; replay sessions and estimate token costs.
Audit Agents/Skills/Commands
Run a quantitative quality audit on agents, skills, and commands to check production readiness and get prioritized recommendations.
NotebookLM Research Agent
End-to-end research-to-content pipeline: ingest sources into Google NotebookLM, run deep cited research, generate downloadable artifacts, and produce polished c