observability

A local telemetry plugin for Claude Code. Telemetry is technical activity data; this plugin records session, tool, and subagent events in a local SQLite database and can optionally send redacted data to external monitoring services.

In plain words
What is it for?
Use it to inspect local activity, show live context and usage in a statusline, or forward redacted signals to Grafana, an OTLP service, or PostHog.
Why use it?
It helps track agent activity and usage while excluding prompts, responses, code, tool data, credentials, and environment values from telemetry payloads. External destinations are opt-in.

Plugin for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add plugins/eigenwise/eigenwise-toolshed/observability
Claude Code
/plugin marketplace add Eigenwise/eigenwise-toolshed
Clone the repo
git clone --depth 1 https://github.com/Eigenwise/eigenwise-toolshed

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

observability scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/observability/.claude-plugin/plugin.json · 24 lines

What it actually says

{
  "name": "observability",
  "version": "0.7.20",
  "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 can forward redacted signals to Grafana, generic OTLP, or PostHog. Telemetry payloads exclude prompts, responses, code, tool inputs and results, credentials, and environment values. Sink configuration you provide, including OTLP headers or tokens, is 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"
  ]
}
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 24 lines scan A 676a963ad69e

Subscribe to this mod's changes

observability is a plugin published in the GitHub repository Eigenwise/eigenwise-toolshed (36 stars, last pushed 3d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other plugins, from other repositories

skarn-guard

Real-time guard on five Claude Code pre-execution hook events (tool calls, permission decisions, submitted and expanded prompts, and subagent creation) plus a response-end advisory that flags an action leaking a secret, installing a malicious package, or exfiltrating data, plus the skarn-audit skill (scan sessions and.

skarn-security/agent-guard · not measured

goalkeeper

Durable goal-following for Claude Code: contracts with definition-of-done, subagent judge gates, and linear chains.

bonfire-systems/goalkeeper · not measured

noisy-tools-in-subagent

Forces noisy commands (builds, tests, linters, static analysis) to run inside a Sonnet subagent instead of the main context, preserving main-agent tokens.

fprochazka/claude-code-plugins · not measured

forge

A generator: it interviews an organization and emits a standalone, org-owned Claude Code plugin (the org's agent harness) aligned to how that org actually works. Karpathy-schema wiki + role/subagent pattern + skill verbs + tool adapters + the operating model. Re-emit to upgrade; never fork.

ktoulgaridis/forge · not measured

coaltipple

CoalTipple — model/effort router for Claude Code. Delegates a task you CAN do but is large+cheap DOWN to a lower tier to save tokens; escalates a task beyond the current tier UP for quality — up to Fable 5, the top rung (a consent-gated, real-money spawn). Two-knob routing (tier × effort, effort-before-tier), an alias.

TheColliery/CoalTipple · not measured

zAI-Skills

Development marketplace for AI-Toolkit, consulting-toolkit, real-estate-investment, career-coach, and plugin-forge plugins.

Aznatkoiny/zAI-Skills · not measured