observability

v0.8.2

Local, metadata-only telemetry for Claude Code. A bundled observer records session, tool, and subagent lifecycle events into SQLite on your machine, an optional statusline shows live context and usage, and an OpenTelemetry Collector forwards redacted signals to the observer. Logs reach configured sinks, including PostHog, through the observer's consent-filtered outbox; traces and metrics use separate Collector sink pipelines for Grafana or generic OTLP. Telemetry payloads exclude prompts, responses, code, tool inputs and results, credentials, and environment values. Exporter settings you provide, including OTLP headers or tokens, are stored locally in %LOCALAPPDATA%\Eigenwise\Workbench\observability.json on Windows, or ~/.local/share/Eigenwise/Workbench/observability.json when LOCALAPPDATA is not set, so an exporter can authenticate. Every sink beyond local SQLite is opt-in.

Claude Code1 Skill

By EigenwiseLicense: MIT278 GitHub starsUpdated last week

Directory evidence

Runtimes: Claude Code
Parsed components: 1 skill or MCP entry
Source updated: Oct 8, 2026
Manifest status: Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install observability for Claude Code

Installs for the current user

claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install observability-3@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually

$ git clone https://github.com/Eigenwise/eigenwise-toolshed

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/observability/.

Plugin files

plugins/observability/

├── .claude-plugin/plugin.json
└── skills/enable-project-telemetry/SKILL.md

Included Skills1

enable-project-telemetryskills/enable-project-telemetry/SKILL.md

Opt the current project into local Claude Code usage telemetry, or verify its setup. Use to enable, disable, or check project telemetry.

Plugin manifests1

plugins/observability/.claude-plugin/plugin.json

{
  "name": "observability",
  "version": "0.8.2",
  "description": "Local, metadata-only telemetry for Claude Code. A bundled observer records session, tool, and subagent lifecycle events into SQLite on your machine, an optional statusline shows live context and usage, and an OpenTelemetry Collector forwards redacted signals to the observer. Logs reach configured sinks, including PostHog, through the observer's consent-filtered outbox; traces and metrics use separate Collector sink pipelines for Grafana or generic OTLP. Telemetry payloads exclude prompts, responses, code, tool inputs and results, credentials, and environment values. Exporter settings you provide, including OTLP headers or tokens, are stored locally in %LOCALAPPDATA%\\Eigenwise\\Workbench\\observability.json on Windows, or ~/.local/share/Eigenwise/Workbench/observability.json when LOCALAPPDATA is not set, so an exporter can authenticate. Every sink beyond local SQLite is opt-in.",
  "author": {
    "name": "Eigenwise",
    "email": "[email protected]"
  },
  "homepage": "https://github.com/Eigenwise/eigenwise-toolshed/tree/main/plugins/observability",
  "repository": "https://github.com/Eigenwise/eigenwise-toolshed",
  "license": "MIT",
  "suiteTimeout": 300000,
  "keywords": [
    "observability",
    "telemetry",
    "opentelemetry",
    "grafana",
    "statusline",
    "metrics",
    "tokens",
    "cost"
  ]
}

Browse the “observability” tag →

arize-ax

by Arize AI

Arize AX platform skills for LLM observability, evaluation, and optimization. Includes trace export, instrumentation, datasets, experiments, evaluators, AI provider integrations, annotations, prompt optimization, and deep linking to the Arize UI.

Agent Plugins

39.8kUpdated last week

phoenix

by Arize AI

Phoenix AI observability skills for LLM application debugging, evaluation, and tracing. Includes CLI debugging tools, LLM evaluation workflows, and OpenInference tracing instrumentation.

Agent Plugins

39.8kUpdated last week

prompt-cache-control

by claude-code-templates

Prompt-cache meter above the Claude Code prompt: how many tokens each request read from, wrote to and sent past the cache, a live countdown to the cache's expiry, and what to do about it (keep going, compact or clear). The TTL follows Claude Code's own rules for your account (1 hour on a Claude subscription, 5 minutes on an API key, cloud provider or usage credits, plus the TTL variables and setting) and corrects itself from request timing. /cache opens a per-turn table.

Claude Code

32.4kUpdated 2 weeks ago

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[observability on Agent Plugins Marketplace](https://pluginsmp.com/plugins/observability-3)