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.
npx agentmods add commands/opensesh/design-ops/dashboardgit clone --depth 1 https://github.com/opensesh/DESIGN-OPSWrote 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/opensesh/design-ops/dashboard)<a href="https://agentmods.dev/commands/opensesh/design-ops/dashboard"><img src="https://agentmods.dev/badge/commands/opensesh/design-ops/dashboard.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.02008 |
| Opus 5 | $0.00000 | $0.01004 |
| Sonnet 5 | $0.00000 | $0.00402 |
| Haiku 4.5 | $0.00000 | $0.00201 |
Grade A, and why
dashboard scanned grade A with 1 finding 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.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -m 2 http://localhost:3847/api/health How it starts
The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/design-ops:dashboard
Live web dashboard that runs as a local server with real-time updates.
New in v2.0: The dashboard now runs as a standalone web server with direct API integration for maximum performance (~50-100ms per API call vs ~500ms+ through MCP).
Trigger
/design-ops:dashboard
What It Does
- Verifies that DESIGN-OPS is configured. If not, routes to
/design-ops:setup. - Verifies the Notion tasks database ID is set in config. If missing, prompts the user for it (or skips if Notion isn't connected).
- Checks if the dashboard server is already running.
- Tells the user how to start it if not — they need to run it from their own terminal so 1Password / env credentials load correctly.
- Opens the UI:
http://localhost:5173in dev, or:3847after a production build.
Features
Three-Pillar Layout
- Operations: Calendar, Tasks, Email
- Design: Commits, PRs
- Analytics: Deployments, Links, Social
Timeframe Toggle
Switch between Daily, Weekly, and Quarterly views with a single click.
Repo Filter
Filter GitHub commits and PRs by specific repository.
Auto-Refresh
Data refreshes every 60 seconds automatically.
Dark Mode
Automatically respects your system preference.
Manual Usage
You can also run the dashboard independently of Claude Code:
cd ~/.claude/plugins/design-ops/dashboard
# Or if using local DESIGN-OPS repo:
cd ~/path/to/DESIGN-OPS/dashboard
# Install dependencies (first time only)
npm install
# Start the server
npm run dev
Then open http://localhost:3847 in your browser.
Required Environment Variables
The dashboard needs these environment variables (loaded via load-design-ops-secrets):
| Variable | 1Password Reference | Used By |
|---|---|---|
GITHUB_PERSONAL_ACCESS_TOKEN |
op://DESIGN-OPS/GitHub Token/credential |
GitHub API |
NOTION_API_KEY |
op://DESIGN-OPS/Notion_API_Key/credential |
Notion API |
GOOGLE_CLIENT_ID |
Google OAuth | Google Calendar |
GOOGLE_CLIENT_SECRET |
Google OAuth | Google Calendar |
GOOGLE_REFRESH_TOKEN |
Google OAuth | Google Calendar |
VERCEL_TOKEN |
op://DESIGN-OPS/Vercel-ops/credential |
Vercel API |
DUB_API_KEY |
op://DESIGN-OPS/Dub.co API/credential |
Dub.co API |
META_ACCESS_TOKEN |
op://DESIGN-OPS/Meta Graph API/access token |
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 · 247 lines · 0 tokens per session scan A eb346664341b
dashboard is a command published in the GitHub repository opensesh/DESIGN-OPS (23 stars, last pushed 3mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,008 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
sentinel
GitHub-aware work monitor - triages issues, PRs, and CI failures.
design-compliance
Audit or generate regulation-specific UI patterns for HIPAA, PCI DSS, or ADA compliance. Use --regulation to target a specific standard.
design-tutorial
Interactive guided tour of Naksha — learn commands through real exercises, discover workflows, and get oriented in under 10 minutes.
design-gdpr
Design GDPR/CCPA-compliant consent flows — cookie banners, consent hierarchy, privacy controls, and data deletion request UI.
design-chatbot
Design a complete chatbot or conversational assistant UI — dialog flows, message bubbles, quick replies, typing indicators, error states, and accessibility.
design-review
Review an existing design for quality — accessibility, usability, visual consistency, content, and motion. Accepts HTML files, Figma URLs, preview servers, or screenshots for visual AI critique.