cache-meter
Gauges how long the conversation's prompt cache stays warm, its hit ratio and misses, and what the next message re-caches once it has gone cold
Plugin-Paket · von HolyGrail
Überblick
cache-meter ist ein Plugin-Paket für KI-Coding-Tools von HolyGrail. Marktplätze, die wir lesen und die es listen: 1 (Community GitHub marketplaces). Wir haben es erstmals am 2026-10-21 gesehen und seither keine Änderung erfasst. Stand unseres Marktplatz-Durchlaufs vom 2026-10-23.
Was es abfragt
- Wird als Plugin-Paket installiert
Keiner der Marktplätze, die wir lesen, veröffentlicht seine Tools oder die abgefragten Einstellungen.
Was es deklariert, abfragt und ausführt, vollständig
Installieren Sie nur Plugins von Entwicklern, denen Sie vertrauen. Wir zeigen, was die Marktplätze veröffentlichen, und testen keine Plugins.
Funktioniert mit
- Claude Code
Nach den Marktplätzen, die ihn listen, und dem angegebenen MCP-Transport, wie jeder Client sie dokumentiert. Wir testen keine Plugins.
Verbinden
Befehle und Konfigurationen nur aus den Angaben der Marktplätze. Wir führen sie nicht für Sie aus und testen keine Plugins.
Als Claude-Code-Plugin
Erstellt aus den Angaben von Community GitHub marketplaces.
/plugin marketplace add holygrail/claude-mods
/plugin install cache-meter@claude-modsWo es veröffentlicht ist
| Marktplatz | Status | Version | Zahlen | Verifiziert | Erstmals gesehen |
|---|---|---|---|---|---|
| Community-Marktplatz holygrail/claude-mods (Quelle auf GitHub öffnen) | Gelistet | 0.1.0 | Forks (GitHub): 1 Sterne (GitHub): 19 |
Nicht markiert |
Jede Zahl stammt vom jeweiligen Marktplatz und wird nie über Marktplätze hinweg addiert. Ein Marktplatz ohne veröffentlichte Zahl zeigt keine: keine Zahl ist nicht null.
In einem Community-Marktplatz gelistet
| Marktplatz | Repository | Sterne (GitHub) |
|---|---|---|
| claude-mods | holygrail/claude-mods | 19 |
Was sich geändert hat
- Wird seitdem als Produkt geführt
- Community GitHub marketplaces: erschienen
Ähnliche Plugins
Produkte, deren eigene Namen, Beschreibungen, Werkzeuge und Skills diesem der Bedeutung nach am nächsten sind, auf allen Marktplätzen, die wir lesen. Die Nähe ist nur innerhalb dieser Liste geordnet.
-
Runs the cache-refund checkup and narrates it: what your prompt cache saved, what it leaked, and (for API users) whether to enable the 1-hour TTL.
-
Keep Claude Code's prompt cache warm across idle pauses. A Stop hook stamps activity and a background Monitor pings the session only after it has been idle long enough (default 50…
-
A prompt cache bar and dashboard for every conversation, subagent and teammate, per-conversation TTLs, and upkeep that keeps an idle cache warm or compacts it.
-
Real-time status line showing context usage, costs, active tools, and session analytics.
-
Analyze Convai sessions, latency, reliability, usage, and provider telemetry via API key.
-
GenPark Tool Call Latency Profiler Metrics
High-resolution MCP tool call latency profiler and P50/P90/P95/P99 telemetry metrics collector
-
ezstat-mcp-server dev.ezstat/ezstat-mcp-server
Track and query EzStat metrics from Claude, Cursor, or any MCP agent. StatHat-compatible.
-
Let your AI sessions talk to each other — messaging, tasks, sessions, and alerts
-
Audits a sample of HTTP request URLs against explicit, documented cache-key standardization rules...
-
Keep the Anthropic prompt cache warm during Claude Code sessions by scheduling lightweight pings at regular intervals, reducing token costs by up to 90% on cached context.
Ähnliche Plugins nach Marktplatz
Dieselbe Frage an jeden Marktplatz einzeln: Gibt es dort ein Gegenstück zu diesem Plugin?
Gelistet auf Claude Code: claude-plugins-community (5)
-
Displays real-time usage percentages (5h session, 7d weekly, context window), reset countdowns, burn rate, and exhaustion prediction in your Claude Code terminal status line…
-
Analyze real user-agent conversations to surface where users get blocked, optimize prompts, and understand what drives engagement or churn
-
OpenTelemetry observability for Claude Code sessions. Captures tool calls, LLM invocations, token usage, and errors as OTel traces. Send telemetry to Dash0 or any…
-
Audit and optimize Claude Code context window usage. Runs a 9-phase analysis covering plugins, hooks, CLAUDE.md cascade, MCP servers, environment settings, zombie process…
-
Langfuse observability plugin for Claude Code — captures and exports traces, spans, and session telemetry from Claude Code to Langfuse for LLM monitoring, debugging, and evaluation
Gelistet auf Claude Code: claude-plugins-official (5)
-
OpenTelemetry observability for Claude Code sessions. Captures tool calls, LLM invocations, token usage, and errors as OTel traces. Send telemetry to Dash0 or any…
-
Connect Claude Code to LogRocket to query session replays, metrics, issues, and user behavior using natural language.
-
Langfuse observability plugin for Claude Code — captures and exports traces, spans, and session telemetry from Claude Code to Langfuse for LLM monitoring, debugging, and evaluation
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
-
Use Datadog directly in Claude Code through a preconfigured Datadog MCP server. Query logs, metrics, traces, dashboards, and more through natural conversation. This plugin is in…
Gelistet auf Claude: knowledge-work-plugins (5)
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
-
Use Datadog directly in Claude Code through a preconfigured Datadog MCP server. Query logs, metrics, traces, dashboards, and more through natural conversation. This plugin is in…
-
Official SigNoz plugin for MCP setup, docs, queries, dashboards, and alerts
-
Hosted MCP server for AI-assisted Grafana Cloud observability — no local installation required.
-
Skills, agents, and workflows for Honeycomb observability — query patterns, production investigations, SLOs, OpenTelemetry instrumentation, and Beeline migration. Designed to…
Gelistet auf Codex: openai-curated (openai/plugins) (5)
-
Available for US1 customers only. Analyze, investigate, and act on your Datadog telemetry directly from ChatGPT using natural language. Ask questions about your production…
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
PostHog gives your AI agent direct access to your product analytics, feature flags, experiments, error tracking, surveys, logs, and LLM analytics. Ask questions about your data…
-
Cloudflare platform plugin with curated skills for Workers, Wrangler, and Agents SDK plus the official Cloudflare API MCP server.
-
Inspect recent issues and events in Sentry from Codex.
Gelistet auf Community GitHub marketplaces (5)
-
Runs the cache-refund checkup and narrates it: what your prompt cache saved, what it leaked, and (for API users) whether to enable the 1-hour TTL.
-
Keep Claude Code's prompt cache warm across idle pauses. A Stop hook stamps activity and a background Monitor pings the session only after it has been idle long enough (default 50…
-
A prompt cache bar and dashboard for every conversation, subagent and teammate, per-conversation TTLs, and upkeep that keeps an idle cache warm or compacts it.
-
Real-time status line showing context usage, costs, active tools, and session analytics.
-
Keep the Anthropic prompt cache warm during Claude Code sessions by scheduling lightweight pings at regular intervals, reducing token costs by up to 90% on cached context.
Gelistet auf Copilot CLI: github/awesome-copilot (5)
-
Shows live prompt-cache reuse, expiry, token composition, and AI Credit cost for the current GitHub Copilot session without making model calls.
-
See your local Copilot token usage by day, model, and session, and get tips to use it more efficiently.
-
Visualizes live session AI-credit usage as a Pac-Man board with pellets, ghosts, fruit milestones, and game-over limits.
-
Use Datadog directly in Copilot / VS Code through a preconfigured Datadog MCP server. Query logs, metrics, traces, dashboards, and more through natural conversation.
-
See a live map of the Copilot agents on your computer, their sub-agents, their commands, and where their data goes.
Gelistet auf Copilot CLI: github/copilot-plugins (5)
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
mcp-apps
Generate MCP App widgets for MCP tools. Produces self-contained HTML widgets using the MCP Apps protocol.
-
Analyze MSVC build performance using vcperf.exe and ETL traces.
-
workiq-productivity
WorkIQ productivity skills powered by the local WorkIQ CLI — read-only insights across email, meetings, calendar, Teams, SharePoint, projects, and people.
-
workiq
Query Microsoft 365 data with natural language — emails, meetings, documents, Teams messages, and more.
Gelistet auf Cursor: cursor/plugins (5)
-
Inspect and manage feature gates, experiments, dynamic configs, and metrics.
-
Work with PostHog from chat: query product analytics and run SQL, manage feature flags and experiments, triage error tracking issues, and review session replays, surveys, and…
-
Track AI visibility, sentiment, and citations.
-
CLI-backed repo compatibility scans plus agents that audit startup, validation, and docs against reality.
-
Scaffold and validate new agent plugins.
Gelistet auf Docker MCP Catalog (5)
-
MCP server providing Prometheus metrics access and PromQL query execution for AI assistants
-
Read and score Opik traces, experiments, datasets and prompts from your AI assistant.
-
MCP Server to interact with a SuzieQ network observability instance via its REST API.
-
mcp-victoriametrics io.github.VictoriaMetrics-Community/mcp-victoriametrics
MCP Server for VictoriaMetrics. Provides integration with VictoriaMetrics API and documentation
-
mcp-grafana io.github.grafana/mcp-grafana
An MCP server giving access to Grafana dashboards, data and more.
Gelistet auf Official MCP Registry (5)
-
Analyze Convai sessions, latency, reliability, usage, and provider telemetry via API key.
-
GenPark Tool Call Latency Profiler Metrics
High-resolution MCP tool call latency profiler and P50/P90/P95/P99 telemetry metrics collector
-
ezstat-mcp-server dev.ezstat/ezstat-mcp-server
Track and query EzStat metrics from Claude, Cursor, or any MCP agent. StatHat-compatible.
-
Let your AI sessions talk to each other — messaging, tasks, sessions, and alerts
-
Audits a sample of HTTP request URLs against explicit, documented cache-key standardization rules...
Gelistet auf PyPI (MCP servers) (5)
-
google-analytics-mcp io.github.surendranb/google-analytics-mcp
GA4 MCP server for AI agents: schema discovery, server-side aggregation, analysis-ready defaults.
-
mcp-server-couchbase io.github.Couchbase-Ecosystem/mcp-server-couchbase
Couchbase Model Context Protocol Server to interact with Couchbase clusters
-
Self-hosted Intervals.icu MCP server: training analytics, Garmin data, wellness, workout planning
-
MCP server for Box admin-log analytics — external-sharing visibility, read-only
-
Monitor uptime, manage incidents, configure alerting, and query dependency status via DevHelm
Gelistet auf npm registry (MCP servers) (5)
-
Evidence-grounded agent memory with mandatory provenance, on local SQLite or Cloudflare D1
-
remem-mcp — Local-first MCP Memory + CodeGraph + Wiki
Local-first memory for AI coding agents. Memory + CodeGraph + Wiki in one SQLite file.
-
Local-first memory for AI coding agents — Markdown + SQLite FTS5, shared across editors via MCP.
-
mcp-google-analytics io.github.leonardosepulvedat/mcp-google-analytics
GA4 MCP that reads AND writes: reports, funnels, audits, and server-side events. 26 tools.
-
gitmem io.github.gitmem-dev/gitmem
Persistent institutional memory for AI coding agents. Memory that compounds.
Nach Bedeutung gefunden, nicht über gemeinsamen Code oder ein gemeinsames Repository: Ähnliche Plugins bleiben getrennte Produkte, und dies ist weder eine Bewertung noch eine Empfehlung.
Möchten Sie dieses Zeichen für Ihr Plugin in unserem Katalog?
Belegen Sie mit einer Datei im Repository, einer Datei auf Ihrer Domain oder einem DNS-Eintrag, dass Sie es pflegen, und Sie können dieses Zeichen auf der Karte zeigen, dazu Live-Banner für Ihre Website und Ihr README. So funktioniert die Verifizierung
Außerdem erhalten Sie Hinweise, wenn ein Marktplatz es aufnimmt, entfernt, sein Verified-Zeichen oder seine Anforderungen ändert, und sein Remote-Endpunkt wird wie ein Webdienst überwacht.
Daten von Community GitHub marketplaces. Die Zahlen stammen aus unseren eigenen regelmäßigen Durchläufen über die Marktplätze, zuletzt abgerufen am . Kontaktdaten von Plugin-Herausgebern veröffentlichen wir nicht.