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 tedydonel/Heisenberg --skill pencil-extractgit clone --depth 1 https://github.com/tedydonel/HeisenbergWrote 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/tedydonel/heisenberg/pencil-extract)<a href="https://agentmods.dev/skills/tedydonel/heisenberg/pencil-extract"><img src="https://agentmods.dev/badge/skills/tedydonel/heisenberg/pencil-extract/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/tedydonel/heisenberg/pencil-extract"><img src="https://agentmods.dev/badge/skills/tedydonel/heisenberg/pencil-extract.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 | $0.00039 | $0.01351 |
| Opus 5 | $0.00019 | $0.00675 |
| Sonnet 5 | $0.00008 | $0.00270 |
| Haiku 4.5 | $0.00004 | $0.00135 |
Grade A, and why
pencil-extract 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.
How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Heisenberg Pencil Extraction
Purpose
Extract the active Pencil design into Heisenberg Blade without treating exported HTML as production code. The source of truth is Pencil MCP node data; HTML exports are structural references only.
Placement
Read docs/file-structure.md before editing.
- Low-level reusable primitives go in
resources/views/components/ui/. - Editor pages, fixtures, layouts, and page composition go in
resources/views/editor/. - Editor CSS goes in
resources/css/editor/. - Editor JavaScript goes in
resources/js/editor/. - Never create an improvised extraction folder.
uiprimitives are leaves: no dependencies on Editor composition, backend services, or futurelivecomponents.
Pencil reading protocol
- Call
mcp__pencil__get_editor_state({include_schema:true})first. - Confirm the active file is the requested Heisenberg
.penfile. - Locate frames with shallow
batch_getsearches. - Read exact reusable nodes and at least one instance at
readDepth: 2–3. - Use
get_screenshotfor visual truth. - Never read
.penfiles through filesystem tools.filePathis only a hint and cannot switch the active document.
If the active document is wrong, stop and ask the user to open the correct file. Never reconstruct a design from memory.
Token discipline
Heisenberg has no CSS build step. There is no Tailwind, no PostCSS, nothing to compile. Styling is plain, hand-written CSS.
Do not hardcode design colors, spacing, radii, font sizes, or borders in extracted output. Every design value must reference the matching custom property from resources/css/tokens.css via var(--hb-x, fallback), where the fallback literal matches that token's current value in tokens.css (resilience if the stylesheet fails to load, not an excuse to skip the variable). For example: border-radius: var(--hb-radius-md, 5px);, color: var(--hb-text-primary, #0A0A0A);.
Never emit a bare literal (border-radius: 5px;, color: #0A0A0A;) for a value that has a matching token. If Pencil has a value without a matching token in tokens.css, stop and report it; do not invent a token or silently substitute a raw value.
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.
- 11d ago First seen · 101 lines · 39 tokens per session scan A 35ba02f7345a
pencil-extract is a skill published in the GitHub repository tedydonel/Heisenberg (104 stars, last pushed 8d ago), licensed Apache-2.0. It adds 39 tokens to every session and 1,351 once invoked, about $0.0002 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.
Other skills, from other repositories
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
frontend-visual-qa
Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.
animation-principles
Apply animation principles — easing, staging, follow-through — to one specific UI motion. Use when tuning how an animation feels. For product-wide duration and easing tokens use motion-system (design-systems); for a full interaction spec use micro-interaction-spec.
refactoring-ui
Audit and fix visual hierarchy, spacing, color, and depth in web UIs. Use when the user mentions "my UI looks off" (or amateur/unprofessional), "fix the design", "Tailwind styling", "color palette", "visual hierarchy", "design system", "spacing scale", or "component styling". Also trigger when building consistent…