ksor: Skill for Claude Code

.agents/skills/site-design/SKILL.md

site-design is a skill for Claude Code, Codex from panaversity/ksor. It costs 134 tokens per session (2,244 once invoked), scanned A, original, Apache-2.0.

A design guide for changing the KSoR website, including its home page, document pages, themes, typography, spacing, and components. KSoR is a system of record: a trusted copy of company knowledge that preserves ownership and source history.

In plain words
What is it for?
Use it when restyling the site, adjusting dark mode or layout, changing visual components, or ensuring pages serve both human readers and software agents.
Why use it?
It explains the product’s design rules and content limits before you change the site, helping prevent changes that conflict with how the system works.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is panaversity/ksor's own configuration. It tells Claude Code and Codex how to work on ksor itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ksor configures →

Reuse

Borrowing it

Nothing to install: this file belongs to panaversity/ksor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/panaversity/ksor/main/.agents/skills/site-design/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/panaversity/ksor

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for site-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/panaversity/ksor/site-design/github.svg)](https://agentmods.dev/skills/panaversity/ksor/site-design)
Your own site
<a href="https://agentmods.dev/skills/panaversity/ksor/site-design"><img src="https://agentmods.dev/badge/skills/panaversity/ksor/site-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.

agentmods 80×15 button for site-design

Your own site · 80×15
<a href="https://agentmods.dev/skills/panaversity/ksor/site-design"><img src="https://agentmods.dev/badge/skills/panaversity/ksor/site-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 134 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,244 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 18 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Memory Poisoning · line 71
    Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.
    Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
  • medium Memory Poisoning · line 74
    Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.
    Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
  • medium Memory Poisoning · line 75
    Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.
    Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
  • medium Memory Poisoning · line 76
    Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.
    Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
  • medium Memory Poisoning · line 77
    Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.
    Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
  • medium Memory Poisoning · line 78
    Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.
    Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
  • medium Memory Poisoning · line 79
    Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.
    Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
  • medium Memory Poisoning · line 80
    Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.
    Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
  • medium Prompt Injection · line 71
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 72
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 74
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 75
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 76
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 77
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 78
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 79
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 80
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 81
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00134 $0.02244
Opus 5 $0.00067 $0.01122
Sonnet 5 $0.00027 $0.00449
Haiku 4.5 $0.00013 $0.00224

Measured 11d ago against content hash 5f6ab003909c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

site-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 11d 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.

.agents/skills/site-design/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Designing the KSoR site

The general craft of visual design is not here — load the frontend-design skill for that (aesthetic direction, type pairing, avoiding templated defaults). This skill is the part that is specific to this product: what the site is, what it may not do, what has already gone wrong, and how a change proves itself. Use both.

What you are designing

A system of record: the copy of the company's knowledge that wins when it and a spreadsheet disagree. Not a docs site, not a marketing site. Its world is charters, registers, custody, provenance, supersession — and its vernacular is worth mining, because that is where distinctive choices come from.

It serves two audiences from one source: a person reading pages, and an agent reading bytes (llms.txt, llms-full.txt, /md/<path>.md). That duality is the product's second principle and the richest thing in the brief — a design that expresses it beats a design that decorates around it.

Four constraints that are not style opinions

  1. The site never contains authored content (scaffolded AGENTS.md, critical rule 1). Every word on a page comes from instance.md or a document's frontmatter. You may write UI labels — "Open the record", "For agents" — but never a sentence that describes the product. If a design needs copy to work, the design is wrong for this product. Design carries the weight instead.
  2. No web fonts. A Google face is fetched at BUILD time, which breaks the offline build and the byte-identical rebuild the scaffold pins — and the browser smoke test asserts zero external requests, so it fails the suite, not just the principle. System stacks only. shadcn init adds next/font/google on its own; revert it every time.
  3. Static export. output: "export". No runtime, no server components that need one, no image optimizer. Interactivity is fine (client components render into the HTML), but anything the BYTES must carry — governance, addresses, statuses — has to be in the server-rendered markup, not behind a click. A crawler, a reader with JavaScript off, and an agent parsing HTML all get what is in the file.
  4. The home page has four jobs and no fifth (research/site-design.md §4): say what the record is authoritative for, name the identity citations carry, open the record, point at the agent doors. A marketing home page is a recorded non-goal.

Read the full file on GitHub · 112 lines

Changes

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.

  1. 11d ago First seen · 112 lines · 134 tokens per session scan A 5f6ab003909c

Subscribe to this mod's changes

site-design is a skill published in the GitHub repository panaversity/ksor (155 stars, last pushed 7d ago), licensed Apache-2.0. It adds 134 tokens to every session and 2,244 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

brand-landingpage

Brand-first landing page designer — runs a brand-identity interview (colors, typography, shape language), then generates and iterates on a polished landing page via Stitch with deployment-ready HTML. Use when the user asks to create, design, or build a landing page, homepage, or marketing page and has no established…

wshobson/agents · 112 tokens

smui

Local copy of the smui ("spacemolt") design system ( ), adapted for the CAD Viewer. smui is a Nord-inspired terminal aesthetic for shadcn/ui with light and dark modes: sharp edges, monospace everything. Read this whole document before restyling viewer UI.

earthtojake/text-to-cad · 0 tokens

web-animation-design

Design and implement web animations that feel natural and purposeful. Use this skill proactively whenever the user asks questions about animations, motion, easing, timing, duration, springs, transitions, or animation performance. This includes questions about how to animate specific UI elements, which easing to use…

vercel-labs/open-agents · 177 tokens

frontend-ui-dark-ts

Build dark-themed React applications using Tailwind CSS with custom theming, glassmorphism effects, and Framer Motion animations. Use when creating dashboards, admin panels, or data-rich interfaces with a refined dark aesthetic.

microsoft/skills · 48 tokens

openkb-html-critic

Use to review a generated HTML deck or single-page artifact for visual quality and structural correctness. Especially good at catching CSS specificity bugs where slide-modifier classes (.divider, .center, .q, .flow etc.) accidentally override the base .slide{display:none} and cause one slide to stack on top of every…

VectifyAI/OpenKB · 132 tokens

design-context-extract

Extract design DNA from app screenshots, live URLs, or screen recordings using Google Stitch — color palettes, typography, spacing tokens, component patterns, and motion specs as design-tokens.json or Tailwind config. Use when the user points to a screenshot, URL, or video and asks to extract or audit the design…

yonatangross/orchestkit · 84 tokens