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/pymodel/designer-skill/designer-setupgit clone --depth 1 https://github.com/PyModel/designer-skillWhat 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 | $0.00013 | $0.00299 |
| Opus 5 | $0.00006 | $0.00150 |
| Sonnet 5 | $0.00003 | $0.00060 |
| Haiku 4.5 | $0.00001 | $0.00030 |
Grade A, and why
designer-setup 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 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.
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
designer-skill Setup
Step 1: Check MCP package
npx -y @pymodel/designer-skill-mcp --version
If this prints a version, the npm package resolves. If not, check Node.js (18+) and network access.
Step 2: Verify MCP is connected
In Cursor: Settings → Tools & MCP — confirm designer-skill is listed and enabled.
Or test from the shell:
npx -y @pymodel/designer-skill-mcp --check-update
Step 3: Smoke test
Ask the agent:
Use designer-skill: call get_preflight_brief, then commit_design_direction for a sample brand landing page direction, then list_commands.
You should see the skill router and command list.
Manual MCP config
If the plugin did not wire MCP, add repo-root mcp.json (or .cursor/mcp.json):
{
"mcpServers": {
"designer-skill": {
"command": "npx",
"args": ["-y", "@pymodel/designer-skill-mcp@latest"]
}
}
}
Pin a version for teams: replace @latest with @0.15.0.
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 · 52 lines · 13 tokens per session scan A c6b3e1e78c89
designer-setup is a command published in the GitHub repository PyModel/designer-skill (30 stars, last pushed 2d ago), licensed MIT. It adds 13 tokens to every session and 299 once invoked, about $0.0001 per session on Opus 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 2026-08-30.
Other commands, from other repositories
run-review
Cross-run review of Design I/O runs — gate table + repeat blockers + rule candidate queue (derived, report-only).
product-dogfood
Dogfood Design I/O once; log process gaps only.
dev-next
Locate the current dev-pipeline stage and drive the next one without glue prompts.
product-grill
Grill design-playbook v0 scope; write CONTEXT/ADR/grill-notes.
run-status
Report Design I/O run phase, blocker, and next resume action.
product-next
Report design-playbook product phase and the single next action.