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 mikeOnBreeze/cc-crossbeam --skill adu-targeted-page-viewergit clone --depth 1 https://github.com/mikeOnBreeze/cc-crossbeamWrote 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/mikeonbreeze/cc-crossbeam/adu-targeted-page-viewer)<a href="https://agentmods.dev/skills/mikeonbreeze/cc-crossbeam/adu-targeted-page-viewer"><img src="https://agentmods.dev/badge/skills/mikeonbreeze/cc-crossbeam/adu-targeted-page-viewer/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/mikeonbreeze/cc-crossbeam/adu-targeted-page-viewer"><img src="https://agentmods.dev/badge/skills/mikeonbreeze/cc-crossbeam/adu-targeted-page-viewer.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 | $0.00134 | $0.01763 |
| Opus 5 | $0.00067 | $0.00881 |
| Sonnet 5 | $0.00027 | $0.00353 |
| Haiku 4.5 | $0.00013 | $0.00176 |
Grade A, and why
adu-targeted-page-viewer 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 12d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ADU Targeted Page Viewer
Overview
Extract a construction plan PDF into page PNGs and build a JSON manifest mapping sheet IDs to page numbers. This enables fast, targeted viewing of specific sheets referenced in corrections letters — without doing deep content extraction of every page.
Speed: Under 2 minutes for the manifest. Individual sheet lookups are instant after that.
Key difference from full extraction: This skill only identifies WHICH page is WHICH sheet. It does not extract content, dimensions, materials, or structural details from each page. That analysis happens on-demand when a specific sheet is requested.
Prerequisites
pdftoppm/pdfinfo(from poppler):apt-get install poppler-utils(Linux) orbrew install poppler(macOS)ImageMagick(for resize + title block cropping):apt-get install imagemagick(Linux) orbrew install imagemagick(macOS)
Workflow
Step 1: Extract All Pages to PNG
Check first: PNGs may already be pre-extracted. Look for pages-png/page-01.png in the project files directory. If PNGs already exist, skip this step entirely — go straight to Step 2.
If PNGs don't exist, run scripts/extract-pages.sh to split the PDF into individual page PNGs:
scripts/extract-pages.sh <input.pdf> <output-dir>
This produces output-dir/pages-png/page-01.png, page-02.png, etc. at 200 DPI (full resolution, no resize). Takes ~5 seconds for a 26-page set. The script is idempotent — if PNGs already exist it exits immediately.
Step 2: Read the Cover Sheet and Find the Sheet Index
Read pages-png/page-01.png visually. The sheet index is typically in the top-right or right-side area of the cover sheet.
Extract the index as a list of entries:
CS → Cover Sheet
A1 → Site Plan
A2 → Floor Plan
A3 → Elevations & Roof Plan
S1.0 → Structural Notes
S2.0 → Foundation Plan
...
This gives the list of expected sheets and their descriptions.
If the index is not on page 1, check page 2 — some sets have a separate title page before the cover sheet.
What ships with it
3 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.
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.
- 12d ago First seen · 160 lines · 134 tokens per session scan A 071c118045e4
adu-targeted-page-viewer is a skill published in the GitHub repository mikeOnBreeze/cc-crossbeam (291 stars, last pushed 6mo ago), licensed MIT. It adds 134 tokens to every session and 1,763 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.
Other skills, from other repositories
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
pdf-extract-create-workflow
Complete PDF lifecycle: download, extract, and generate structured documents with reportlab.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.
pdf-text-extraction-fallback-85d5ca
Fallback workflow for extracting text from PDFs when readfile returns binary data.
pdf-verification-cli
Verify PDF page count and content using command-line tools when Python libraries unavailable.