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 darellchua2/opencode-config-template --skill cad-redraw-skillgit clone --depth 1 https://github.com/darellchua2/opencode-config-templateWrote 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/darellchua2/opencode-config-template/cad-redraw-skill)<a href="https://agentmods.dev/skills/darellchua2/opencode-config-template/cad-redraw-skill"><img src="https://agentmods.dev/badge/skills/darellchua2/opencode-config-template/cad-redraw-skill/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/darellchua2/opencode-config-template/cad-redraw-skill"><img src="https://agentmods.dev/badge/skills/darellchua2/opencode-config-template/cad-redraw-skill.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 | $0.00076 | $0.01928 |
| Opus 5.5 | $0.00030 | $0.00771 |
| Sonnet 5.5 | $0.00015 | $0.00386 |
| Haiku 4.5 | $0.00008 | $0.00193 |
Grade A, and why
cad-redraw-skill 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 1mo 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CAD redraw and validation (Linux / ezdxf)
Provenance: the workflow methodology follows pengxiaoan/autocad-dwg-redraw-skill (evidence levels, fingerprint-first redraw, visual-vs-dimensional separation). That repository ships no license, so no code was copied — this skill is a clean-room reimplementation on ezdxf for Linux. The installed files are the runtime source of truth.
Purpose
Reconstruct an editable, validated 2D CAD drawing from one of three input types, entirely on Linux with no AutoCAD and no Windows:
- Mode A — source redraw: a trustworthy DXF (or DWG) exists. Fingerprint it, rebuild it, and prove the rebuild with a fingerprint diff.
- Mode B — PDF-to-DXF: a PDF exists but no CAD source. Extract vector paths into an auditable intermediate DXF, labeled PDF-derived — never claimed as original-CAD-exact.
- Mode C — image-to-CAD: only a raster reference (photo, scan, screenshot). Build an evidence-aware spec, draw from it, and compare visually without ever asserting dimensional accuracy from pixels.
Use this skill when
The user asks for a dwg redraw, to redraw dxf content, convert image to dxf,
pdf to dxf, raster to CAD, or to fingerprint and validate a drawing rebuild.
For 3D solids hand off to the cad-generation-skill (load via skill tool);
this skill is 2D only. the cad-dxf-skill (load via skill tool) generates
new parametric drawings; this skill reconstructs existing ones.
Non-negotiable rules
- Resolve geometry in this order: explicit user requirements, readable dimensions, derived constraints, calibrated measurements, labeled visual estimates. Image pixels never override a written dimension.
- Track every important value as
known,scaled,inferred, orunreadable. - Visual similarity never proves dimensional accuracy. Comparison output is labeled "visual only".
- Conflicting dimensions are never silently resolved: record the conflict
and return
needs_revieworblocked. - Never overwrite the source file. Always write to a new output path.
- PDF-derived and image-derived outputs are labeled as such. An intermediate is never presented as an exact original CAD source.
What ships with it
11 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.
- references/linux-toolchain.md 3.6 KB
- references/redraw-spec.md 4.0 KB
- references/validation.md 3.2 KB
- scripts/compare_visual.py 13 KB runs code
- scripts/fingerprint_diff.py 12 KB runs code
- scripts/fingerprint.py 18 KB runs code
- scripts/pdf_vector_to_dxf.py 8.8 KB runs code
- scripts/preflight_image.py 13 KB runs code
- scripts/render_preview.py 4.9 KB runs code
- scripts/spec_to_dxf.py 45 KB runs code
- scripts/to_dwg.py 6.1 KB runs code
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.
- 1mo ago First seen · 169 lines · 76 tokens per session scan A 85fce03dcb13
cad-redraw-skill is a skill published in the GitHub repository darellchua2/opencode-config-template (6 stars, last pushed 28d ago), licensed Apache-2.0. It adds 76 tokens to every session and 1,928 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-19.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.