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 Ed3Design/ed3design-engineering-bundles --skill image-to-mesh-cad-workflowgit clone --depth 1 https://github.com/Ed3Design/ed3design-engineering-bundlesWrote 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/ed3design/ed3design-engineering-bundles/image-to-mesh-cad-workflow)<a href="https://agentmods.dev/skills/ed3design/ed3design-engineering-bundles/image-to-mesh-cad-workflow"><img src="https://agentmods.dev/badge/skills/ed3design/ed3design-engineering-bundles/image-to-mesh-cad-workflow/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/ed3design/ed3design-engineering-bundles/image-to-mesh-cad-workflow"><img src="https://agentmods.dev/badge/skills/ed3design/ed3design-engineering-bundles/image-to-mesh-cad-workflow.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 | $0.00222 | $0.07050 |
| Opus 5 | $0.00111 | $0.03525 |
| Sonnet 5 | $0.00044 | $0.01410 |
| Haiku 4.5 | $0.00022 | $0.00705 |
Grade A, and why
image-to-mesh-cad-workflow 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 — 488 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image-to-Mesh CAD Workflow
A pragmatic pipeline for translating a 2D concept image into a parametric CAD model in Fusion 360 when manual spline-tracing produces visible deviation from intent.
⚠️ RECURRING TRAP — Read This Before Every Operation ⚠️
The single most expensive recurring failure mode in this workflow is falling back to spec/text descriptions for dimensions, positions, and orientations instead of measuring them from the mesh. This trap is sneaky because:
- The spec document is psychologically authoritative (it's a written record). The mesh is just data that needs to be measured. So when in doubt, the spec wins by default.
- User-feedback-driven adjustments ("make it bigger", "rotate it") feel like they should be applied directly. But the user's intent is almost always "match the mesh better" — which means measuring the mesh, not eyeballing.
- After fixing one component (e.g., correcting the main-body orientation), other components built earlier in the wrong frame are silently invalid. They look fine in the timeline but are semantically wrong.
Real cost from one rotationally-symmetric speaker-housing session:
- 4 hours debugging a 180°-X-flip that mesh-audit would have surfaced in 30 seconds
- 3 cut-size iterations (50×40, 100×60, then learned the mesh actually has 122×50) — each took ~30 minutes plus user-correction wait time
- Inner cone left mis-oriented for an entire session because nobody re-validated it after the main-body fix
- One destructive 15mm fillet on a 6mm wall (volume 1255 → 566 cm³) because radius-vs-wall-thickness wasn't checked first
Real cost from a follow-up session:
- 3 wrong cone-position iterations (translation Z=-7 → -12 → -9 → -7.7) because the cut-window Z-range was estimated from spec docs (-7.7..-2.7) instead of measured from body edges (-8.3..-2.1 inner edge, -7.7..-2.7 outer edge — different per face due to wall curvature)
- Translation
occ.transform2 = msilently reverted to a previous value (Z=-4.5 instead of the just-set Z=-9) because timeline recompute restored an older state — never verified post-set, user had to re-flag the wrong position - → Maxim: "In constructions, always measure, never estimate." Applies to every dimension, position, and any value you just set.
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 · 488 lines · 222 tokens per session scan A fdeb9ee9821c
image-to-mesh-cad-workflow is a skill published in the GitHub repository Ed3Design/ed3design-engineering-bundles (2 stars, last pushed 1mo ago), licensed MIT. It adds 222 tokens to every session and 7,050 once invoked, about $0.0011 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 2026-08-31.
Other skills, from other repositories
design-system
Creates the Tamagui brand system for an Expo/React Native Power Apps mobile app, including design-system.md, tokens.ts, and an HTML gallery.
canvas-app
Creates or edits a Power Apps Canvas App through the Canvas Authoring MCP coauthoring session. Handles new app generation, direct targeted edits, complex multi-screen changes, responsive layout, per-screen self-QA, and compile-error convergence. Trigger on requests to create, build, generate, modify, update, change…
top-design
Create award-winning, immersive web experiences at the level of Awwwards-featured agencies. Use when the user mentions "Awwwards quality", "make my site stunning", "scroll animations", "parallax storytelling", "cinematic web design", "portfolio site", or "brand experience". Also trigger when elevating a standard…
design-everyday-things
Apply foundational design principles: affordances, signifiers, constraints, feedback, and conceptual models. Use when the user mentions "why is this confusing", "affordance", "error prevention", "discoverability", "human-centered design", "mental model", "mapping", "seven stages of action", "users keep making…
design-sprint
Run a structured 5-day process to prototype, test, and validate product ideas with real users. Use when the user mentions "design sprint", "validate before we build", "rapid prototype", "test with users", or "should we build this". Also trigger when a team is stuck in endless debate over a high-stakes product…
steve-jobs-design-review
Review designs, products, and features with Steve Jobs' standards: ruthless simplicity, focus, and end-to-end excellence. Use when the user mentions "Steve Jobs review", "design review", "product review", "what would Steve do", "insanely great", "this feels too complicated", "too many features", "product taste"…