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 m-binimran/dev-pack --skill design-directiongit clone --depth 1 https://github.com/m-binimran/dev-packWrote 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/m-binimran/dev-pack/design-direction)<a href="https://agentmods.dev/skills/m-binimran/dev-pack/design-direction"><img src="https://agentmods.dev/badge/skills/m-binimran/dev-pack/design-direction/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/m-binimran/dev-pack/design-direction"><img src="https://agentmods.dev/badge/skills/m-binimran/dev-pack/design-direction.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 | $0.00047 | $0.00384 |
| Opus 5.5 | $0.00019 | $0.00154 |
| Sonnet 5.5 | $0.00009 | $0.00077 |
| Haiku 4.5 | $0.00005 | $0.00038 |
Grade A, and why
design-direction 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
design-direction
The fastest way to ship template-looking UI is to start coding without a direction. Don't.
Do this first
- Pick a named direction — editorial/magazine, neo-brutalism, glass-with-real-depth, dark or light luxury, bento, scrollytelling, Swiss/International, retro-futurism. NOT "clean minimal." NOT auto dark mode.
- Palette intentionally: a base, 1–2 surfaces, a semantic accent (success/warn/danger), and ONE
brand-defining color used with purpose. Define as Tailwind v4
@themetokens (hand totheme-tokens). - Type pairing: a display/heading face with character + a readable body face. State the pairing and why.
- Reference set: name 2–3 real sites/products this should feel like.
- Motion intent: how motion clarifies this product (subtle micro vs. cinematic scroll). Hand to
animation-implement.
Output
- A short "direction brief": style name, palette tokens, type pairing, references, motion intent.
- This brief is the contract the rest of the build is judged against.
Guardrails (anti-template)
- Every surface must show ≥4 of: scale hierarchy, spacing rhythm, depth/layering, real type, semantic color, designed interaction states, grid-breaking composition, texture, purposeful motion, designed data viz.
- Final gut check: "would this look believable in a real product screenshot?" If no, iterate before building more.
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 · 28 lines · 47 tokens per session scan A 44ff71f93581
design-direction is a skill published in the GitHub repository m-binimran/dev-pack (2 stars, last pushed 4mo ago), licensed MIT. It adds 47 tokens to every session and 384 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
codoop-discover
Launch a collaborative product discovery session with multi-role experts (PM, GTM, UI, Architect). Use when exploring 0-to-1 design for a new product or feature. Orchestrates expert agents in-session to draft comprehensive backlog documentation through SNAP clarification, multi-perspective analysis, and consistency…
codoop-ux-walkthrough
Simulate a real task from a chosen user persona and write an evidence-backed, non-blocking experience report. Use after building a user-facing feature, when reviewing a runnable product flow, or when product owners want user-perspective improvement ideas without changing code automatically.
frontend-design-quality
Ensure frontend design work follows established repo patterns, minimizes clicks, fills real viewports, stays responsive, avoids text overflow, reduces portal UI clutter, covers content-rich surfaces such as blogs/resources, and is verified with Playwright or equivalent visual screenshots. Use when building, changing…
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.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).