What is Observability?

A live dashboard for monitoring activity across multiple coding agents. It displays sessions, tool calls, hook events, timelines, and traces as they happen.

Use it to start, stop, restart, or inspect a local dashboard that streams agent activity in real time.

It makes multi-agent workflows easier to inspect and helps identify where an agent process is behaving unexpectedly.

Observability — Skill for Claude Code by CarbeneAI

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.

Any agent

npx skills add CarbeneAI/Forge --skill observability

Clone the repo

git clone --depth 1 https://github.com/CarbeneAI/Forge

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/carbeneai/forge/observability/github.svg)](https://agentmods.dev/skills/carbeneai/forge/observability)

Your own site

<a href="https://agentmods.dev/skills/carbeneai/forge/observability"><img src="https://agentmods.dev/badge/skills/carbeneai/forge/observability/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/carbeneai/forge/observability"><img src="https://agentmods.dev/badge/skills/carbeneai/forge/observability.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,036 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00049	$0.01036
Opus 5	$0.00024	$0.00518
Sonnet 5	$0.00010	$0.00207
Haiku 4.5	$0.00005	$0.00104

Measured 6d ago against content hash 4c0f788c22ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

Observability scanned grade B with 2 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 6d ago.

The scan reads SKILL.md. This mod also ships 16 executable files (apps/client/postcss.config.js, apps/client/src/composables/__tests__/useAdvancedMetrics.example.ts, apps/client/src/composables/useAdvancedMetrics.ts, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- Check hooks are configured in `~/.claude/settings.json`

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Check server is running: `curl http://localhost:4000/health`

.claude/skills/Observability/SKILL.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Observability Dashboard

Real-time monitoring of PAI multi-agent activity with WebSocket streaming.

Quick Start

# Start server and dashboard
~/.claude/skills/observability/manage.sh start

# Stop everything
~/.claude/skills/observability/manage.sh stop

# Restart both
~/.claude/skills/observability/manage.sh restart

# Check status
~/.claude/skills/observability/manage.sh status

Access Points

Dashboard UI: http://localhost:5172
Server API: http://localhost:4000
WebSocket Stream: ws://localhost:4000/stream

What It Monitors

Real-Time Tracking

Agent session starts/ends
Tool calls across all agents
Hook event execution
Session timelines and traces
WebSocket live updates

Data Sources

Primary: ~/.claude/history/raw-outputs/YYYY-MM/YYYY-MM-DD_all-events.jsonl
Format: JSONL with structured event data
Hooks: Events logged automatically by PAI hook system

Architecture

Stack:

Server: Bun + Express + TypeScript
Client: Vite + Vue + TypeScript
Storage: In-memory streaming (no database)
Protocol: WebSocket for real-time updates

Key Features:

Watch filesystem with automatic reload
Tail-follow for today's event file
Cache events in-memory
Broadcast WebSocket to all clients
No persistence (fresh start each launch)

When to Activate This Skill

"Start observability"
"Stop the dashboard"
"Restart observability"
"Monitor agents"
"Show agent activity"
"Observability status"
"Debug agent workflow"

Examples

Example 1: Start monitoring agents

User: "start observability"
→ Launches server on port 4000
→ Starts dashboard on port 5172
→ Opens browser to live agent activity view

Example 2: Debug a stuck workflow

User: "something's weird with my agents, show me what's happening"
→ Opens observability dashboard
→ Shows real-time tool calls across all agents
→ Reveals which agent is blocked or looping

Example 3: Check dashboard status

User: "is observability running?"
→ Runs manage.sh status
→ Reports server and client running state
→ Shows access URLs if active

Read the full file on GitHub · 161 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

6d ago First seen · 161 lines · 49 tokens per session scan B 4c0f788c22ce

Subscribe to this mod's changes

Observability is a skill published in the GitHub repository CarbeneAI/Forge (9 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 1,036 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Analytics and metrics Building agents Claude Code ai-agents ai-ops cybersecurity devsecops open-source

scanning-containers-with-trivy-in-cicd

This skill covers integrating Aqua Security's Trivy scanner into CI/CD pipelines for comprehensive container image vulnerability detection. It addresses scanning Docker images for OS package and application dependency CVEs, detecting misconfigurations in Dockerfiles, scanning filesystem and git repositories, and…

xalgorix/xalgorix · 74 tokens

implementing-code-signing-for-artifacts

This skill covers implementing code signing for build artifacts to ensure integrity and authenticity throughout the software supply chain. It addresses signing binaries, packages, and containers using GPG, Sigstore, and platform-specific signing tools, establishing trust chains, and verifying signatures in deployment…

xalgorix/xalgorix · 62 tokens

Observability