dashboard

dashboard is a command for Claude Code from ArieGoldkin/claude-forge. It costs 20 tokens per session (875 once invoked), scanned B, original, MIT.

A command that starts and opens a local dashboard for monitoring coding-agent sessions. The dashboard shows live tool use, errors, agents, and session measurements.

In plain words
What is it for?
Use it to start the session monitor, open it in a browser, and watch session activity in real time.
Why use it?
It gives developers a live view of what their sessions are doing instead of relying only on terminal output.

Command for Claude Code

Written for Claude Code: PostToolUse hook event. Also seen: reads .claude/ paths; mentions Claude Code.

Part of the ctk plugin — 12 commands, 1 agent shipped together

Good fit Use it to start the session monitor, open it in a browser, and watch session activity in real time.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/ariegoldkin/claude-forge/dashboard
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.

Clone the repo
git clone --depth 1 https://github.com/ArieGoldkin/claude-forge

Made for: Claude Code.

Or install ctk, the plugin that ships this one along with the rest of its 12 commands, 1 agent.

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.

agentmods badge for dashboard

README.md
[![agentmods](https://agentmods.dev/badge/commands/ariegoldkin/claude-forge/dashboard/github.svg)](https://agentmods.dev/commands/ariegoldkin/claude-forge/dashboard)
Your own site
<a href="https://agentmods.dev/commands/ariegoldkin/claude-forge/dashboard"><img src="https://agentmods.dev/badge/commands/ariegoldkin/claude-forge/dashboard/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.

agentmods 80×15 button for dashboard

Your own site · 80×15
<a href="https://agentmods.dev/commands/ariegoldkin/claude-forge/dashboard"><img src="https://agentmods.dev/badge/commands/ariegoldkin/claude-forge/dashboard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 875 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00020 $0.00875
Opus 5.5 $0.00008 $0.00350
Sonnet 5.5 $0.00004 $0.00175
Haiku 4.5 $0.00002 $0.00088

Measured 1mo ago against content hash 0ff44898955e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

dashboard 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 1mo ago.

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.

Place this in your **user-level** settings (`~/.claude/settings.json`) to monitor all projects, or in a project's `.claude/settings.json` for project-specific monitoring.

Makes network callslowCapability

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

curl -s http://localhost:3117/api/sessions > /dev/null 2>&1
plugins/continuity-toolkit/commands/dashboard.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/dashboard - Live Session Monitor

Start the Claude Session Monitor and open the live dashboard in your browser.

Prerequisites

The session monitor must be installed:

cd ~/projects/claude-session-monitor
npm install

What This Command Does

  1. Check if the monitor server is already running on port 3117
  2. If not running, start it in the background
  3. Open the dashboard in your browser at http://localhost:3117
  4. The dashboard shows real-time session activity via Server-Sent Events

Execution Steps

Step 1: Check if monitor is running

curl -s http://localhost:3117/api/sessions > /dev/null 2>&1

If the above succeeds, the monitor is already running — skip to Step 3.

Step 2: Start the monitor

# Find the monitor project
MONITOR_DIR="${CLAUDE_SESSION_MONITOR_DIR:-$HOME/projects/claude-session-monitor}"

if [ ! -f "$MONITOR_DIR/package.json" ]; then
  echo "Claude Session Monitor not found at $MONITOR_DIR"
  echo "Install: git clone <repo-url> $MONITOR_DIR && cd $MONITOR_DIR && npm install"
  exit 0
fi

# Start in background
cd "$MONITOR_DIR" && npx tsx src/cli.ts --no-open &
sleep 2

Step 3: Open dashboard

open http://localhost:3117

Step 4: Verify connection

The dashboard should show "Connected" in the top-right corner. As you work in Claude Code, events will appear in real-time if HTTP hooks are configured.

HTTP Hook Configuration

For the monitor to receive events, add HTTP hooks to your project's .claude/settings.json or the plugin's hooks.json:

{
  "hooks": {
    "PostToolUse": [{ "url": "http://localhost:3117/events", "timeout": 1000 }],
    "SessionStart": [{ "url": "http://localhost:3117/events", "timeout": 1000 }],
    "SessionEnd": [{ "url": "http://localhost:3117/events", "timeout": 1000 }],
    "Stop": [{ "url": "http://localhost:3117/events", "timeout": 1000 }],
    "PostToolUseFailure": [{ "url": "http://localhost:3117/events", "timeout": 1000 }],
    "SubagentStart": [{ "url": "http://localhost:3117/events", "timeout": 1000 }],
    "SubagentStop": [{ "url": "http://localhost:3117/events", "timeout": 1000 }],
    "UserPromptSubmit": [{ "url": "http://localhost:3117/events", "timeout": 1000 }],
    "PreCompact": [{ "url": "http://localhost:3117/events", "timeout": 1000 }]
  }
}

Read the full file on GitHub · 105 lines

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. 1mo ago First seen · 105 lines · 20 tokens per session scan B 0ff44898955e

Subscribe to this mod's changes

dashboard is a command published in the GitHub repository ArieGoldkin/claude-forge (7 stars, last pushed 2mo ago), licensed MIT. It adds 20 tokens to every session and 875 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.