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/FlorianBruniaux/claude-code-pluginsWrote 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/florianbruniaux/claude-code-plugins/web)<a href="https://agentmods.dev/commands/florianbruniaux/claude-code-plugins/web"><img src="https://agentmods.dev/badge/commands/florianbruniaux/claude-code-plugins/web/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/florianbruniaux/claude-code-plugins/web"><img src="https://agentmods.dev/badge/commands/florianbruniaux/claude-code-plugins/web.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 | $0.00009 | $0.00475 |
| Opus 5.5 | $0.00004 | $0.00190 |
| Sonnet 5.5 | $0.00002 | $0.00095 |
| Haiku 4.5 | $0.00001 | $0.00047 |
Grade A, and why
ccboard-web 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 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.
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.
What it actually says
Web Interface Command
Launch the ccboard web UI for browser-based monitoring and visualization.
Features
- Web Dashboard: Access ccboard from any browser
- Live Updates: Server-Sent Events (SSE) for real-time data
- Responsive Design: Works on desktop, tablet, mobile
- Same Data: Shares data layer with TUI (single binary)
- Concurrent Access: Multiple users can view simultaneously
Usage
# Launch web UI on default port 3333
/ccboard-web
# Or specify custom port
ccboard web --port 8080
Access
Once launched, open in your browser:
http://localhost:3333
Modes
ccboard supports 3 execution modes:
-
TUI only (default):
ccboard -
Web only:
ccboard web --port 3333 -
Both simultaneously:
ccboard both --port 3333Runs TUI in terminal + web server on port 3333
Web UI Features
- Dashboard with real-time stats
- Sessions browser with pagination
- Configuration viewer (read-only)
- Hooks, agents, costs visualization
- MCP server status
- History and search
Requirements
ccboard must be installed. Run /ccboard-install if needed.
Implementation
#!/bin/bash
# Check if ccboard is installed
if ! command -v ccboard &> /dev/null; then
echo "❌ ccboard is not installed"
echo "Run: /ccboard-install"
exit 1
fi
# Default port
PORT="${1:-3333}"
echo "🌐 Launching ccboard web interface..."
echo "Access at: http://localhost:$PORT"
echo ""
echo "Press Ctrl+C to stop"
echo ""
# Launch web UI
exec ccboard web --port "$PORT"
Note: Web UI is currently in development. TUI is the primary interface with full feature set.
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 · 95 lines · 9 tokens per session scan A b4583d887a26
ccboard-web is a command published in the GitHub repository FlorianBruniaux/claude-code-plugins (42 stars, last pushed 1mo ago), licensed MIT. It adds 9 tokens to every session and 475 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-09-04.
Other commands, from other repositories
review
Deep code review command. Comprehensive code analysis across security, performance, and architecture.
team
Virtual eng team orchestrator. Runs a goal end-to-end through the whole team — strategy → plan → build → QA → ship — conducted by the engineering-manager, delegating to every specialist. One entry point that connects /ceo-review, /eng-review, /qa, and /ship.
content-generate
Social media content generation command. Produces ready-to-use posts, captions, visual briefs, and hashtags for the given platform and type.
health
System health check. Audits dependencies, security, performance, and (if present) the production domain with a triple scan.
security-scan
Security scan. Searches the codebase and dependencies for vulnerabilities and produces a severity-ranked report.
changelog
Automatic changelog generation. Produces a structured changelog from commit history.