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/setupgit clone --depth 1 https://github.com/opensesh/DESIGN-OPSWhat 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 | $0.00000 | $0.14228 |
| Opus 5 | $0.00000 | $0.07114 |
| Sonnet 5 | $0.00000 | $0.02846 |
| Haiku 4.5 | $0.00000 | $0.01423 |
Grade C, and why
setup scanned grade C 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 2d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
2. Run: chmod 755 ~/.claude Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
1. Check if MCP exists and is connected (read `~/.claude/settings.json`) How it starts
The opening of the file, as written. The whole thing — 2,116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/design-ops:setup
Main onboarding wizard for DESIGN-OPS. Guides users through connecting data sources across three business pillars: Operations, Design, and Analytics.
Trigger
User runs /design-ops:setup to configure the plugin. Works in:
- Claude Code CLI (terminal) — full interactive setup
- Claude Desktop (Code tab) — full interactive setup
- Claude Co-work (web) — read-only mode, directs to terminal
Design Philosophy
This setup flow is tool-agnostic and outcome-driven:
- Ask what tools they use, discover how to connect
- Evaluate each tool for MCP or API capabilities
- Let users select what data they want in their briefs
- Adapt to whatever combination of tools the user has
Pre-Flight Check
Before starting, detect the environment and existing setup:
1. Environment Detection
if (web/co-work environment detected):
Show current config status
Display: "For full setup, run /design-ops:setup in Claude Code CLI"
Exit early
1.5 Secrets Manager Detection (1Password-First)
Design principle: 1Password is the PRIMARY path for secrets management. Make it the default, not just an option.
Check for available secrets managers before proceeding with tool setup:
# Detection order (check for CLI availability)
1. 1Password CLI: `which op` or `op --version`
2. Bitwarden CLI: `which bw`
3. macOS Keychain: `which security` (fallback)
4. None detected
If 1Password detected (primary path):
## Secure Secrets Management
**1Password CLI detected!** (`op` command available)
Your API keys will be stored securely in 1Password. This keeps credentials:
- Out of plain text files (safer)
- Easy to rotate when keys expire
- Shareable with your team
- With an audit trail of access
**This is the recommended approach.** As we set up each tool that needs an API key,
I'll help you store it in 1Password automatically.
[Continue with 1Password (recommended)] | [I'll manage secrets myself]
Note: The default button is "Continue with 1Password" — not a list of equal options.
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.
- 2d ago First seen · 2,116 lines · 0 tokens per session scan C b4ea3a79db33
setup 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 14,228 tokens. A static security scan graded it C with 2 findings (asks for root, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
design-tutorial
Interactive guided tour of Naksha — learn commands through real exercises, discover workflows, and get oriented in under 10 minutes.
motion-design
Design micro-interactions, transitions, and animation systems for UI components or full pages.
design-critique
UX heuristic review of Figma screens — evaluates against Nielsen's 10 heuristics, visual design quality, spacing, color, typography hierarchy, and interaction states.
oss
Daily OSS contribution check - uses CLI with --json for structured data.
setup-oss
Configure OSS autopilot preferences.
nyann:diff-profile
Compare two nyann profiles side-by-side and show what changes between them: hooks, branching, CI, documentation, extras, governance. Useful before switching profiles to understand the impact.