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 build-with-dhiraj/ai-workflow-framework-portability-kit --skill jove-design-loopgit clone --depth 1 https://github.com/build-with-dhiraj/ai-workflow-framework-portability-kitWrote 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/build-with-dhiraj/ai-workflow-framework-portability-kit/jove-design-loop)<a href="https://agentmods.dev/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/jove-design-loop"><img src="https://agentmods.dev/badge/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/jove-design-loop/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/build-with-dhiraj/ai-workflow-framework-portability-kit/jove-design-loop"><img src="https://agentmods.dev/badge/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/jove-design-loop.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 | $0.00144 | $0.02301 |
| Opus 5.5 | $0.00058 | $0.00920 |
| Sonnet 5.5 | $0.00029 | $0.00460 |
| Haiku 4.5 | $0.00014 | $0.00230 |
Grade A, and why
jove-design-loop 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.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project root: every relative path in this skill (
knowledge/...,tools/...,.claude/skills/...) resolves against~/dev/jove-hq, never the current working directory. This skill is invocable from any cwd, so prefix accordingly:~/dev/jove-hq/knowledge/jove-labs/STATUS.md.
JoVE design loop (See → Spec → Build → Ship)
Purpose: dev should never be idle waiting on a Figma frame that doesn't exist yet, and Colleague-V should never face a blank canvas. This skill turns Colleague-V's own Figma exports into a designed-vs-owed ledger, then builds clickable strawmen for the owed items on the JoVE Design System so the dev lead/Colleague-S/Colleague-P can start today. Colleague-V keeps full visual authority — the loop removes the specification dependency, not the design one. Crossing that line reads as "Dhiraj now ships his own designs" and burns the relationship and the CEO's "less is more" bar; every prototype this skill produces is a strawman with an explicit right-of-refusal, never a finished screen.
Gate (run first)
- Read
~/.claude/jove-watchdog/jove-design-loop-cache.md(this skill's own cache). It holds the last CSS-export fingerprint, the last frame-index build, and which JVA tickets already have a prototype attached. Never re-diff or re-catalogue what it already covers; only process what changed. - On-demand only, same as jove-labs-sweep. Never scheduled, never run unprompted.
- There is no Figma Dev-seat dependency for this skill. A View seat hits the Figma MCP's tool-call rate limit almost immediately (confirmed 14 Jul 2026) — don't route through
mcp__figma__*live reads for this loop. Everything here runs off the exports Dhiraj drags out of Figma's File > Export, which need no seat upgrade and no credential of any kind.
Station 1 — SEE (build the designed-vs-owed ledger)
Ask Dhiraj to re-export from Figma whenever he says Colleague-V has pushed something: File > Export the CSS (produces a revamp css file) and File > Export selected frames as PNG (produces a Figma PNGs/ folder), both usually landing in ~/Downloads. The .fig file itself is a dead end for reading — it's Figma's binary format, only useful for dragging straight into Claude Design (see Station 3).
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 · 71 lines · 144 tokens per session scan A cc978259e6fc
jove-design-loop is a skill published in the GitHub repository build-with-dhiraj/ai-workflow-framework-portability-kit (5 stars, last pushed 21d ago), licensed MIT. It adds 144 tokens to every session and 2,301 once invoked, about $0.0006 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
interaction-skill
Layer A interaction-mechanics reference anchored to the beui.dev catalog. Stacks on any style skill whenever work adds or changes motion or interaction — micro-interactions, animated components, transitions, gestures, hover/press/state feedback, loading/success/error morphs, 'make it feel alive'. Mandates reading the…
vertical-site-conventions
Compose pages and sites that read as their vertical: ecommerce-catalog storefronts that look like storefronts, hospitality-food sites that look like restaurants, b2b-manufacturer sites that look industrial. Use this skill whenever the user wants to build a site that looks like the vertical it serves, fix a build that…
ui-design
Designs and builds React/Next/Tailwind UI, audits visual and interaction defects, and stress-tests components with worst-case data. Use when asked to "build a landing page", "extract our design system", "add dark mode", "make this responsive", "remove UI slop", "audit this component", "stress-test this component"…
suede-design
Suede AI design skill for interfaces that feel intentional instead of templated: design tokens, color strategy, OKLCH ramps, type scale, fluid type, visual hierarchy, dark mode, spacing, component laws, motion, full surface builds that ship layout and words together, reference-to-target restyles (Suedify), and…
gsap
Expert guidelines for building high-performance animations with GSAP (GreenSock Animation Platform).
typography-scale-builder
Build a complete typographic system -- modular or fluid type scale, line-height and tracking per size, weight roles, and vertical rhythm -- exported as tokens, Tailwind config, and CSS. Pairs with font-pairing-suggester (which picks the fonts; this builds the system they live in).