Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/harshii0509/designStacknpx agentmods add skills/harshii0509/designstack/polishWrote 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/harshii0509/designstack/polish)<a href="https://agentmods.dev/skills/harshii0509/designstack/polish"><img src="https://agentmods.dev/badge/skills/harshii0509/designstack/polish/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/harshii0509/designstack/polish"><img src="https://agentmods.dev/badge/skills/harshii0509/designstack/polish.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 | $0.00051 | $0.00922 |
| Opus 5.5 | $0.00020 | $0.00369 |
| Sonnet 5.5 | $0.00010 | $0.00184 |
| Haiku 4.5 | $0.00005 | $0.00092 |
Grade A, and why
ds-polish 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preamble
"../lib/env.sh" "polish"
What this skill does
Think of this as the final check before you hit publish. I'll look at your site through 11 different lenses — from "does it look good?" to "can everyone use it?" — and tell you exactly what to fix before sharing with the world.
This is the release gate. If the user only wants one-screen visual QA, route them to /ds-look. If they want cross-page brand consistency, route them to /ds-brand.
Takes about 3–5 minutes.
"Checking 11 areas before you share this. Takes 3–5 minutes. I'll tell you what needs fixing and what's already great."
Step 1 — Get the URL
Ask:
"What's the main page you want to polish before sharing? (e.g.
http://localhost:3000or your live site)."
If the user asks for multiple pages, tell them:
"Let's do the most important page first.
/ds-polishis the final release gate for one page at a time. If you want a multi-page consistency scan, use/ds-brand."
Step 2 — Load context
If DESIGN_BIBLE is yes, read it for brand rules.
Note from Memory Log any recent confirmed intentional changes.
Step 3 — Run all 11 checks
For each check, take a screenshot and extract what you need. Describe findings in plain English.
Read references/checklist.md and run all 11 checks in order, following its commands, thresholds, and plain-English result patterns.
Step 4 — Write the polished report
Follow the jargon rules in lib/plain-language.md when writing this report — no technical terms.
Pre-launch check for [URL]
Overall: [Ready to share / A few things to fix / Needs work before launch]
Score: [X]/11 checks passed
✓ Already great: [List checks that passed — give credit for what's working]
⚠️ Fix before sharing:
[For each failed check:] [Check name] — [Plain English description of the issue] How to fix: [Specific plain-English fix] How long: [Quick (1 min) / Short (5-10 min) / Takes a while]
My top 3 fixes (do these now):
- [Most visible or impactful issue]
- [Second most important]
- [Third]
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 119 lines · 51 tokens per session scan A f08302f74cff
ds-polish is a skill published in the GitHub repository harshii0509/designStack (13 stars, last pushed 4mo ago), licensed MIT. It adds 51 tokens to every session and 922 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 2026-08-30.
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.
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).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.