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 DKeken/codex-skills-alternative --skill design-sharegit clone --depth 1 https://github.com/DKeken/codex-skills-alternativeWrote 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/dkeken/codex-skills-alternative/design-share)<a href="https://agentmods.dev/skills/dkeken/codex-skills-alternative/design-share"><img src="https://agentmods.dev/badge/skills/dkeken/codex-skills-alternative/design-share/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/dkeken/codex-skills-alternative/design-share"><img src="https://agentmods.dev/badge/skills/dkeken/codex-skills-alternative/design-share.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 | $0.00092 | $0.00898 |
| Opus 5 | $0.00046 | $0.00449 |
| Sonnet 5 | $0.00018 | $0.00180 |
| Haiku 4.5 | $0.00009 | $0.00090 |
Grade A, and why
design-share 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design — Share
Get the prototype in front of reviewers with a working link + clear run notes. Final handoff stage. The goal is that someone who wasn't involved can open it, know what to look at, and leave useful feedback — without you in the room.
When to use
- A QA'd prototype is ready to circulate for feedback.
- "Share it", "give me a link", "publish", "let the team see it".
- Handing off to stakeholders for review/sign-off.
When NOT to use
- The prototype hasn't passed
design-qa(especially HIGH items) — fix or explicitly flag first. - It's not runnable yet →
design-prototype.
Inputs
- The QA'd prototype (path).
- Share method: local serve, tunnel, or deploy to a host.
- Host/account constraints — ask before deploying anywhere external.
Workflow
- Confirm it runs clean: install + build + start. Fix any breakers before sharing.
- Pick the share method:
- Local — serve on a port; give the localhost URL + start command (good for solo/local review).
- Tunnel — expose local via a tunnel; only if the user wants external access right now.
- Deploy — push to a preview host (Vercel/Netlify/etc.). Only with explicit user go-ahead, since it sends code off-machine.
- Write a review note: what to look at, the happy path to click, known stubs/TODOs, where to leave feedback.
- Return the link + run instructions + review note.
Worked example
method: local serve (user wants to review on their machine)
preflight: `npm install` ok, `npm run build` clean, `npm run dev` boots :5173 ✓
deliverable:
link: http://localhost:5173
run: `npm install && npm run dev`
review this: complete the onboarding happy path (Welcome → Template → Name → Dashboard);
check the empty-name error and the loading state on "Create"
known stubs: templates are 3 fixtures; "Create" writes to in-memory store (no real API yet)
feedback: leave notes in #design-review or as comments on the Figma frame
(If deploy was requested: confirm host, check for secrets/env files, deploy, return the live URL + same review note.)
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.
- 9d ago First seen · 65 lines · 92 tokens per session scan A 8a70ec0039f7
design-share is a skill published in the GitHub repository DKeken/codex-skills-alternative (15 stars, last pushed 3mo ago), licensed MIT. It adds 92 tokens to every session and 898 once invoked, about $0.0005 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 skills, from other repositories
fec-web-workers
A Web Worker moves expensive JavaScript calculations into a separate browser thread so the page's main thread can handle input, scrolling, and animation. Workers cannot directly access the page's DOM.
web-scraping
Mass crawl/scrape sites incl. anti-bot (Cloudflare, Akamai, DataDome, PerimeterX). Crawl4AI = scale (arunmany, dispatchers, deep crawl, LLM-ready markdown); Camoufox = fingerprint evasion. For: scrape N pages, crawl a site, extract structured data, 403/challenge/bot-detection, captcha.
page-health-check
A procedure for checking a web page from a URL for data, visual, interaction, console, and performance problems, then fixing or documenting them.
multi-select-reorder
Use when the user wants an interactive ad hoc web page for choosing multiple options and reordering them before submitting.
content-script-developer
Expert in browser extension content scripts, DOM integration, and safe page augmentation across modern web apps. Use when building or updating a browser-extension content script, injecting UI into third-party pages, or handling SPA navigation and dynamic DOM changes.
a11y-debugging
Uses Chrome DevTools MCP for accessibility (a11y) debugging and auditing based on web.dev guidelines. Use when testing semantic HTML, ARIA labels, focus states, keyboard navigation, tap targets, and color contrast.