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/chakra-ui/ark/zaggit clone --depth 1 https://github.com/chakra-ui/arkWhat 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 | $0.00008 | $0.00153 |
| Opus 5 | $0.00004 | $0.00077 |
| Sonnet 5 | $0.00002 | $0.00031 |
| Haiku 4.5 | $0.00001 | $0.00015 |
Grade A, and why
zag 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
Steps
- Make sure the component is installed
- Install it for every framework if it’s not
- Check the
[component]-types.d.tsfile to understand it’s api and anatomy - Implement the component similar to the
[framework]/components/avatar/src - Styling a component happens in
.storybook/styles(as CSS) so we can share across frameworks- No Tailwind
- No style prop
- Create an example folder and agree with me on the list of examples before working on it
- After examples are created, create or update the stories file based on the framework
- Repeat for all frameworks (please ask before moving on to the next framework)
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 · 17 lines · 8 tokens per session scan A e47bc673361b
zag is a command published in the GitHub repository chakra-ui/ark (5,367 stars, last pushed 3d ago), licensed MIT. It adds 8 tokens to every session and 153 once invoked, about $0.0000 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
init
Initialize a project for on-brand Marmo UI generation — detect or interview for brand basics (layout, primary color, fonts, radius, spacing) and write a DESIGN.md if one doesn't exist.
override
Override an @marmoui/ui component or create a new custom component in the app's local ui/ folder — sets up the wrapper convention (src/ui/ re-exporting @marmoui/ui) on first run, then shadows or adds components without forking the package.
prototype
Scaffold a shareable Marmo prototype with the comments + AI-edit overlay pre-wired. Deploys to Netlify and returns a public URL reviewers can sign into with Claude.
design-md
Generate a portable DESIGN.md (brand color, type, tokens, component inventory) at the project root so any AI agent can generate on-brand UI.
marmo-build
Build UI with @marmoui/ui following the full MCP-backed workflow. Use for explicit "build this Marmo way" requests.
gt-workflow
Use Graphite (gt) instead of git for ALL branch and commit operations in this repository.