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/superdesigndev/superdesign-skill/commitgit clone --depth 1 https://github.com/superdesigndev/superdesign-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 | $0.00011 | $0.00408 |
| Opus 5 | $0.00005 | $0.00204 |
| Sonnet 5 | $0.00002 | $0.00082 |
| Haiku 4.5 | $0.00001 | $0.00041 |
Grade A, and why
commit 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 yesterday.
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
Git Commit Task
Analyze the current git changes and create a commit following these instructions:
Instructions
-
First, run
git statusto see all changes -
Run
git diffto review unstaged changes -
Run
git diff --cachedto review staged changes -
Analyze all changes and draft an appropriate commit message that:
- Summarizes the nature of the changes (new feature, enhancement, bug fix, refactoring, etc.)
- Uses conventional commit format (feat:, fix:, refactor:, docs:, style:, test:, chore:, etc.)
- Focuses on the "why" rather than the "what"
- Is concise (50 characters or less for the subject line)
-
Stage relevant files with
git add -
Create the commit using ONLY the user's git config (no Co-Authored-By or Claude attribution)
-
Use this exact format for the commit:
git commit -m "your commit message here"
Important Notes
- DO NOT include any Claude Code attribution
- DO NOT add Co-Authored-By headers
- DO NOT include any emoji or "Generated with Claude Code" text
- Use only the user's configured git author information
- Ensure the commit message accurately reflects the changes
- Follow the repository's existing commit message style based on recent commits
Example
If the changes are about adding a new feature for user authentication, the commit might be:
git commit -m "feat: add user authentication with JWT tokens"
Now proceed to analyze the current changes and create an appropriate commit.
Notice，before OpenPR，you should change branch to main in https://raw.githubusercontent.com/superdesigndev/superdesign-skill/[branch]/skills/superdesign/SUPERDESIGN.md of SKILL.md.
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.
- yesterday First seen · 47 lines · 11 tokens per session scan A f46846415f6f
commit is a command published in the GitHub repository superdesigndev/superdesign-skill (486 stars, last pushed 11d ago), licensed MIT. It adds 11 tokens to every session and 408 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
database-setup
Use when a project needs to store data and has no database yet. Setting up Supabase, creating tables, writing queries, and connecting them to the frontend. Written for designers.
review
Cold re-quiz on code that already shipped — your own session commits, not the change in front of you.
design-critic
Use when you want an honest read on a design instead of encouragement. What is wrong, ranked by severity, with the reason attached. Works on a screenshot, a mockup, or a described screen.
interaction-designer
Use when deciding how something should behave rather than how it looks. Click and tap targets, gestures, keyboard paths, loading and empty and error states, and the feedback each action gives.
color-specialist
Use when colour is failing. Contrast below AA, a palette with no system behind it, dark mode that is only inverted light mode, or semantic colours that carry no meaning.
form-designer
Use when a form is losing people. Too many fields, validation that interrupts typing, unclear required fields, a multi-step flow with no sense of progress, or inputs with no labels.