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 pantheon-org/tekhne --skill web-reference-sheet-generatorgit clone --depth 1 https://github.com/pantheon-org/tekhneWrote 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/pantheon-org/tekhne/web-reference-sheet-generator)<a href="https://agentmods.dev/skills/pantheon-org/tekhne/web-reference-sheet-generator"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/web-reference-sheet-generator/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/pantheon-org/tekhne/web-reference-sheet-generator"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/web-reference-sheet-generator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00143 | $0.01520 |
| Opus 5 | $0.00072 | $0.00760 |
| Sonnet 5 | $0.00029 | $0.00304 |
| Haiku 4.5 | $0.00014 | $0.00152 |
Grade A, and why
web-reference-sheet-generator 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 8d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Design Reference Sheet Generator
Generate a project-specific design reference sheet and companion enforcement skill from any website codebase, mirroring the structure of the Figma Web Design Reference Sheet.
Mindset
Document what exists, not what should exist.
Every invented token is technical debt dressed as documentation — developers trust the
reference sheet and will use the wrong values in production. When data is missing, write
TBD — not yet defined. A reference sheet with honest gaps is more useful than one with
plausible fictions.
When to Use
Apply this skill when:
- Starting a new project and needing a living design token reference
- Onboarding a design system from an existing codebase
- Creating a Figma-compatible reference for designers and developers
- Auditing existing styles to identify undocumented or orphaned tokens
- Porting design tokens between frameworks
Workflow
See references/workflow.md for the full 8-step generation process:
-
Discover design tokens
grep -r "\-\-" src/ --include="*.css" -h | grep -E "^\s+--" | sort -u grep -r "@theme\|@font-face\|@import" src/ --include="*.css" -
Inspect existing components (read 3–5 representative files)
-
Check dark mode and accessibility patterns
-
Fill
templates/skill-output.yaml— structured scratchpad validated againstschemas/design-reference.schema.json -
Generate
docs/design/design-reference.mdfrom the template# Review populated scratchpad before generating final docs cat templates/skill-output.yaml | grep -E "TBD|null" && echo "Gaps found — fill before generating" -
Generate the enforcement skill from the enforcement skill template
bun run generate --template enforcement-skill --output ./{project-slug}/SKILL.md
What ships with it
26 files 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.
- .audits/2026-04-08/analysis.md 1.2 KB
- .audits/2026-04-08/audit.json 512 B
- .audits/2026-04-08/remediation-plan.md 2.6 KB
- .audits/latest 10 B
- .tessl-plugin/plugin.json 1006 B
- CHANGELOG.md 736 B
- evals/eval-01-tailwind-v4-project.md 2.5 KB
- evals/eval-02-plain-css-dark-mode.md 2.7 KB
- evals/eval-03-sparse-codebase-tbd-handling.md 2.2 KB
- evals/scenario-01.md 4.0 KB
- evals/scenario-02.md 4.1 KB
- evals/scenario-03.md 3.4 KB
- references/accessibility-guidelines.md 11 KB
- references/design-reference-template.md 6.9 KB
- references/elements-of-design.md 7.6 KB
- references/enforcement-skill-template.md 3.3 KB
- references/gestalt-principles.md 8.5 KB
- references/grid-and-layout-theory.md 8.3 KB
- references/principles-of-design.md 8.6 KB
- references/psychology-of-color.md 10.0 KB
- references/typography-principles.md 7.8 KB
- references/visual-hierarchy.md 7.9 KB
- references/whitespace-theory.md 8.0 KB
- references/workflow.md 4.4 KB
- schemas/design-reference.schema.json 8.6 KB
- templates/skill-output.yaml 3.5 KB
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.
- 8d ago First seen · 148 lines · 143 tokens per session scan A 9dddd9082773
web-reference-sheet-generator is a skill published in the GitHub repository pantheon-org/tekhne (10 stars, last pushed yesterday), licensed MIT. It adds 143 tokens to every session and 1,520 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 2026-09-03.
Other skills, from other repositories
frontend-ui-engineering
Builds production-quality, accessible, responsive user-facing UIs. Use when building or modifying interfaces and pages, creating components, implementing layouts, meeting WCAG accessibility requirements, managing state, or when the output needs to look and feel production-quality rather than AI-generated.
playground
Creates interactive HTML playgrounds — self-contained single-file explorers that let users configure something visually through controls, see a live preview, and copy out a prompt. Use when the user asks to make a playground, explorer, or interactive tool for a topic.
frontend-design
Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.
baseline-ui
Quickly deslop UI code by fixing spacing, hierarchy, typography, and small layout issues. Use when the interface needs a fast cleanup or polish pass.
web-design-engineer
Build or redesign polished browser-rendered visual artifacts with HTML/CSS/JavaScript/React: pages, dashboards, prototypes, slide decks, animations, UI mockups, and data visualizations. Use for visual front-end creation, design-system exploration, design critique, or explicit browser acceptance / QA of a web artifact.…
frontend-design
A guide for building polished web interfaces such as pages, dashboards, applications, posters, and reusable React or Vue components. It covers visual direction, layout, typography, colors, animation, accessibility, and working HTML, CSS, or JavaScript code.