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.
git clone --depth 1 https://github.com/ArieGoldkin/claude-forgeWrote 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.
[](https://agentmods.dev/commands/ariegoldkin/claude-forge/dashboard)<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.
<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>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 | $0.00020 | $0.00875 |
| Opus 5.5 | $0.00008 | $0.00350 |
| Sonnet 5.5 | $0.00004 | $0.00175 |
| Haiku 4.5 | $0.00002 | $0.00088 |
Grade B, and why
dashboard scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Place this in your **user-level** settings (`~/.claude/settings.json`) to monitor all projects, or in a project's `.claude/settings.json` for project-specific monitoring. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://localhost:3117/api/sessions > /dev/null 2>&1 How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dashboard - Live Session Monitor
Start the Claude Session Monitor and open the live dashboard in your browser.
Prerequisites
The session monitor must be installed:
cd ~/projects/claude-session-monitor
npm install
What This Command Does
- Check if the monitor server is already running on port 3117
- If not running, start it in the background
- Open the dashboard in your browser at http://localhost:3117
- The dashboard shows real-time session activity via Server-Sent Events
Execution Steps
Step 1: Check if monitor is running
curl -s http://localhost:3117/api/sessions > /dev/null 2>&1
If the above succeeds, the monitor is already running — skip to Step 3.
Step 2: Start the monitor
# Find the monitor project
MONITOR_DIR="${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 }]
}
}
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.
- 1mo ago First seen · 105 lines · 20 tokens per session scan B 0ff44898955e
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.
Other commands, from other repositories
workflow-classify
Classify task size (S/M/L/XL) and recommend the appropriate workflow pipeline.
pull-repos
Pull all repos (parent + marketplace clones + configured project repos).
update-counts
Explicitly refresh public toolkit and committed marketplace source snapshots and numeric documentation.
sonarqube
Analyze SonarCloud quality issues for a specific PR.
plan-start
5-phase planning command: PRD analysis, design review, technical decisions, dynamic research team, metrics. Produces a complete implementation plan + ADRs before any code is written.
refactor
Analyze code for SOLID violations and suggest targeted improvements.