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/mishahanin/heading-osnpx agentmods add skills/mishahanin/heading-os/pencil-exportWrote 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/mishahanin/heading-os/pencil-export)<a href="https://agentmods.dev/skills/mishahanin/heading-os/pencil-export"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/pencil-export/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/mishahanin/heading-os/pencil-export"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/pencil-export.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 | $0.00198 | $0.03560 |
| Opus 5 | $0.00099 | $0.01780 |
| Sonnet 5 | $0.00040 | $0.00712 |
| Haiku 4.5 | $0.00020 | $0.00356 |
Grade A, and why
pencil-export 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 7d 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 — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/pencil-export - Export a Pencil deck (WSL-safe)
Pencil writes an export to the wrong disk when it receives a WSL path. The app
normalises \\wsl.localhost\<distro>\... to /<distro>/..., drops the prefix,
and resolves the remainder from the root of C:. It then reports success. A
requested write to /Ubuntu-24.04/home/me/deck.html lands at
C:\Ubuntu-24.04\home\me\deck.html, and nothing warns you.
So this skill stages every export on C: and collects the result from /mnt/c.
Never pass Pencil a WSL path for writing.
Pencil 42.5.0 exposes four MCP tools: execute, get_app_state, browser, and
get_guidelines. Export runs inside execute:
Export(nodeIds, "png"|"jpeg"|"webp"|"pdf"|"html-tailwind"|"html-css", outputPath, options)
Native PNG and PDF are correct at 2x. Use them. The chromium renderer stays for the editable PPTX and the self-contained HTML, which Pencil cannot produce.
Background and full diagnosis: auto-memory pencil-export-nodes-broken-wsl.
Phase 0 - Context
- Open the target
.penas the active editor in the Pencil desktop app.executefails with "wrong .pen file" when no document is active. - Read the registered path with
get_app_state({include_schema:false, include_canvas_design:false, include_scripts_and_shaders:false}). Pass that exact string asfilePathon everyexecutecall. - The first
get_app_stateafter a cold start can return no active editor. Retry it before you report a failure. - Locate the deck directory. Output lands in
<deck-dir>/export/. - Brand fonts: GT Standard and 31C Horizontal. They live in the DATA overlay,
under
brand/fonts/inside the datastore. Resolve that path in Phase 2. Never pass a baredatastore/brand/fontsto Bash. Bash resolves it against the engine root, where the datastore does not exist.
Phase 1 - Select the slides and export
-
Collect the top-level frames and their names:
Print(JSON.stringify(Get((n,c)=>c.depth===0 && n.type==="frame" ? {id:n.id,name:n.name,x:n.x,y:n.y} : undefined)))
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.
- 7d ago First seen · 259 lines · 198 tokens per session scan A ca4aff5d9dbf
pencil-export is a skill published in the GitHub repository mishahanin/heading-os (11 stars, last pushed 2d ago), licensed Apache-2.0. It adds 198 tokens to every session and 3,560 once invoked, about $0.0010 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
PDF files: create, read, merge, fill, OCR, edit text.
hive.pdf
Read, write, merge, split, rotate, watermark, encrypt, and OCR PDF files using Python (pypdf, pdfplumber, reportlab, pypdfium2) and command-line tools (poppler-utils, qpdf). Use when the user asks to extract text/tables/images from a PDF, create or modify a PDF, combine or split PDFs, OCR a scanned PDF…
solidworks-engineering-drawing
A SolidWorks skill for creating and reviewing engineering drawings, which are manufacturing documents showing views, measurements, holes, parts lists, and title-block information.
google-apps-script
Build Google Apps Script automation for Sheets and Workspace. Custom menus, triggers (onEdit / time-driven / form submit), dialogs, sidebars, email batches, PDF export, external API. Use whenever the user wants to automate a Google Sheet, build a Sheets menu / sidebar / dialog, hit a Sheets row from email or a…
design-export-repair
Fixes broken decks/PDFs exported from Claude's "Design" feature (or similar AI deck generators) — cut-off or clipped text, wrong/substituted fonts, and corrupted .pptx package structure that shows up only once you export to PDF, not while looking at it in the app. Use this skill whenever the user uploads a zip, .pptx…
anydoc
Convert Word (.doc/.docx/.docm), PowerPoint (.ppt/.pps/.pot/.pptx/.pptm/.ppsx/.ppsm), Excel (.xls/.xlsx/.xlsm/.xlsb), OpenDocument (.odt/.ods/.odp), RTF, EPUB, CSV, and PDF documents to clean GitHub-Flavored Markdown locally with the Any Doc CLI (npx -y @firecrawl/[email protected]): headings, GFM tables, slide structure…