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 Abhinavbwj/Claude-skills-for-Computational-Designers --skill optimization-methodsgit clone --depth 1 https://github.com/Abhinavbwj/Claude-skills-for-Computational-DesignersWrote 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/abhinavbwj/claude-skills-for-computational-designers/optimization-methods)<a href="https://agentmods.dev/skills/abhinavbwj/claude-skills-for-computational-designers/optimization-methods"><img src="https://agentmods.dev/badge/skills/abhinavbwj/claude-skills-for-computational-designers/optimization-methods/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/abhinavbwj/claude-skills-for-computational-designers/optimization-methods"><img src="https://agentmods.dev/badge/skills/abhinavbwj/claude-skills-for-computational-designers/optimization-methods.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 | $0.00033 | $0.10711 |
| Opus 5 | $0.00016 | $0.05355 |
| Sonnet 5 | $0.00007 | $0.02142 |
| Haiku 4.5 | $0.00003 | $0.01071 |
Grade A, and why
optimization-methods 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- optimization-methods — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 783 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Optimization Methods for AEC Computational Design
1. Optimization in AEC Design
The Role of Optimization
Optimization is the systematic process of finding the best solution from a set of feasible alternatives according to one or more criteria. In the Architecture, Engineering, and Construction (AEC) industry, optimization transforms design from an intuition-driven craft into a rigorous, evidence-based discipline that can explore thousands of alternatives in the time a human designer evaluates a handful.
Every AEC project embeds optimization problems whether practitioners recognize them or not. Selecting a column grid that minimizes steel tonnage, arranging rooms to maximize adjacency satisfaction, routing ductwork to minimize pressure loss, or shaping a facade to balance daylight and solar heat gain -- all are optimization problems with design variables, objectives, and constraints.
Design Optimization vs. Mathematical Optimization
Mathematical optimization seeks a global or local extremum of a function subject to constraints, governed by theorems about convexity, differentiability, and feasibility. Design optimization in AEC adds layers of complexity:
- Multiple stakeholders with conflicting objectives (cost vs. aesthetics vs. performance)
- Mixed variable types: continuous (member thickness), discrete (bolt count), categorical (material grade), topological (connectivity)
- Expensive evaluations: a single FEA run may take minutes; a CFD simulation hours; an energy model tens of minutes
- Ill-defined objectives: "architectural quality" resists quantification
- Regulatory constraints: building codes, zoning ordinances, fire safety -- hard constraints that cannot be relaxed
- Manufacturing constraints: available section catalogs, sheet sizes, fabrication tolerances
- Uncertainty: loads are probabilistic, material properties vary, construction tolerances exist
Problem Classification
| Classification Axis | Categories | AEC Examples |
|---|---|---|
| Variable type | Continuous, discrete, integer, mixed, combinatorial | Member sizing (continuous), bolt count (integer), material choice (categorical) |
| Objective count | Single-objective, multi-objective, many-objective (>3) | Weight minimization (single), weight vs. cost vs. carbon (many) |
| Constraint type | Unconstrained, equality-constrained, inequality-constrained, bound-constrained | Stress <= allowable, drift <= H/400, area = target |
| Landscape | Convex, non-convex, multi-modal, discontinuous, noisy | Topology optimization (non-convex), layout optimization (multi-modal) |
| Evaluation cost | Cheap (analytical), moderate (FEA), expensive (CFD), very expensive (coupled multi-physics) | Truss weight (cheap), building energy (expensive) |
| Determinism | Deterministic, stochastic, robust, reliability-based | Deterministic sizing, reliability-based design under seismic uncertainty |
What ships with it
2 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.
- 11d ago First seen · 783 lines · 33 tokens per session scan A 03456b457349
optimization-methods is a skill published in the GitHub repository Abhinavbwj/Claude-skills-for-Computational-Designers (212 stars, last pushed 5mo ago), licensed MIT. It adds 33 tokens to every session and 10,711 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
optimization-methods
Genetic algorithms, simulated annealing, particle swarm optimization, gradient-based methods, topology optimization, shape optimization, size optimization, and benchmark problems for AEC computational design.
generative-design
Evolutionary algorithms, multi-objective optimization, design space exploration, fitness function design, population-based methods, and generative workflows for AEC computational design.
pysr
Use when fitting equations to data with PySR or SymbolicRegression.jl, when a user wants an interpretable formula, symbolic model, scaling law, or empirical relation discovered from numeric data, or when debugging a PySR search that is slow, stuck, or giving poor equations.
multi-objective-optimization
Pareto-aware molecular design balancing multiple ADMET properties simultaneously. Based on MultiMol (Yu 2025) and MOLLM (Ran 2025).
ml-training-recipes
Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning…
cuopt-developer
Modify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI). Use for solver internals, PRs, DCO, and code conventions.