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 skills add amitvijapur/cortex --skill cortex-frontend-designgit clone --depth 1 https://github.com/amitvijapur/cortexWrote 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/skills/amitvijapur/cortex/cortex-frontend-design)<a href="https://agentmods.dev/skills/amitvijapur/cortex/cortex-frontend-design"><img src="https://agentmods.dev/badge/skills/amitvijapur/cortex/cortex-frontend-design/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/amitvijapur/cortex/cortex-frontend-design"><img src="https://agentmods.dev/badge/skills/amitvijapur/cortex/cortex-frontend-design.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00033 | $0.00517 |
| Opus 5.5 | $0.00013 | $0.00207 |
| Sonnet 5.5 | $0.00007 | $0.00103 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
cortex-frontend-design 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 1mo 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
Cortex frontend library
This skill points to one maintained library in the Cortex checkout. Resolve this
SKILL.md's real path when installed through a symlink; ../../frontend/README.md
from its directory is the library entry point. Read that entry point first.
If the checkout moved, report the broken link and use the project's own design
brief until the dedicated installer is rerun from the new location.
For design work, inspect the project's brief, tokens and constraints before selecting library references. Project requirements take precedence over the library's aesthetic suggestions. Load only the relevant guidance:
| Need | Library file |
|---|---|
| New interface or visual direction | guidance/PLAYBOOK.md, then the relevant prompt in guidance/PROMPT-PACK.md |
| Existing interface critique or hardening | Relevant sections of guidance/CHECKLISTS.md |
| Find a reference, book or implementation resource | resources.json; search title, purpose, tags and category |
| Choose specialist work | guidance/SKILL-MAP.md |
| Capture a discovery or a lesson from a project | README.md contribution instructions |
The skill map records workflows that informed the original kit. Check the active session's skill catalogue before choosing one. A historical name or file on disk does not prove a tool is callable. Use available equivalents or the guidance directly; adding a resource does not install its tools.
Explain the relevance of the small set of references selected. Distinguish inspiration, documentation, and project-tested evidence. The dated legacy guide is an archival reading copy; maintained guidance and resources.json are authoritative. Verify current APIs with official documentation when implementing a dependency.
When asked to add a resource, update resources.json once, validate and rebuild the directory using the scripts documented in README.md. Record source, purpose, tags, and meaningful notes. Only mark a resource tested when there is concrete project evidence. At a project milestone, propose useful discoveries and lessons; do not silently turn them into universal design rules. Keep private screenshots, paid assets, client identities, and local file paths in the local companion folder.
Jaspr remains an optional reference if it comes up; do not install it or change a project's stack just because it appears in the library. Flutter and Dart can be catalogued with explicit platform tags when relevant to a project.
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.
- 1mo ago First seen · 46 lines · 33 tokens per session scan A ae7f8dfc4468
cortex-frontend-design is a skill published in the GitHub repository amitvijapur/cortex (5 stars, last pushed 3d ago), licensed MIT. It adds 33 tokens to every session and 517 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-21.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
webgl-liquid-iridescence
A self-contained WebGL2 hero: a living oil-on-water field brightened into iridescent caustic filaments; move the cursor to bend the flow.
cocoindex-diagrams
This skill should be used when creating, editing, or reviewing inline SVG diagrams for the CocoIndex docs site (anything under docs/src/content/docs/). It encodes the component-based primitive system under docs/src/components/diagrams/, the palette + shape semantics, the preview-and-verify loop using headless Chrome…
cuopt-routing-api-python
Vehicle routing (VRP, TSP, PDP) with cuOpt — Python API only. Use when the user is building or solving routing in Python.
dashboard-design
Use this skill first when the user wants to design or plan a dashboard, especially Vizro dashboards. Enforces a 3-step workflow (requirements, layout, visualization) before implementation. Activate when the user asks to create, design, or plan a dashboard. For implementation, use the dashboard-build skill after…
holoscan-module-lifecycle
Develop external Holoscan Modules with the Holoscan CLI and use them in Holoscan applications: scaffold, test, Python bindings, DEB/WHEEL packaging, and clean-consumer proof.