structural-computation

structural-computation is a skill for Claude Code from Abhinavbwj/Claude-skills-for-Computational-Designers. It costs 33 tokens per session (11,806 once invoked), scanned A, original, MIT.

A guide to computational structural design for buildings and other structures. It explains methods for analyzing forces and using them to shape or improve shells, gridshells, frames, and other structural systems.

In plain words
What is it for?
Use it for finite element analysis, form-finding, shell and gridshell design, topology and shape optimization, material-aware studies, and performance-based structural geometry.
Why use it?
It helps connect a structure's shape, materials, weight, strength, and movement instead of treating structural checks as a final separate step. It provides concepts for evaluating designs against structural and environmental goals.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the Claude-skills-for-Computational-Designers plugin — 18 skills shipped together

Good fit Use it for finite element analysis, form-finding, shell and gridshell design, topology and shape optimization, material-aware studies, and performance-based structural geometry.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/abhinavbwj/claude-skills-for-computational-designers/structural-computation
Install

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.

Any agent
npx skills add Abhinavbwj/Claude-skills-for-Computational-Designers --skill structural-computation
Clone the repo
git clone --depth 1 https://github.com/Abhinavbwj/Claude-skills-for-Computational-Designers

Made for: Claude Code.

Or install Claude-skills-for-Computational-Designers, the plugin that ships this one along with the rest of its 18 skills.

Wrote 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.

agentmods badge for structural-computation

README.md
[![agentmods](https://agentmods.dev/badge/skills/abhinavbwj/claude-skills-for-computational-designers/structural-computation/github.svg)](https://agentmods.dev/skills/abhinavbwj/claude-skills-for-computational-designers/structural-computation)
Your own site
<a href="https://agentmods.dev/skills/abhinavbwj/claude-skills-for-computational-designers/structural-computation"><img src="https://agentmods.dev/badge/skills/abhinavbwj/claude-skills-for-computational-designers/structural-computation/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.

agentmods 80×15 button for structural-computation

Your own site · 80×15
<a href="https://agentmods.dev/skills/abhinavbwj/claude-skills-for-computational-designers/structural-computation"><img src="https://agentmods.dev/badge/skills/abhinavbwj/claude-skills-for-computational-designers/structural-computation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 11,806 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00033 $0.11806
Opus 5 $0.00016 $0.05903
Sonnet 5 $0.00007 $0.02361
Haiku 4.5 $0.00003 $0.01181

Measured 11d ago against content hash ca38839e0efc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

structural-computation 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/structural-computation/SKILL.md · 700 lines

How it starts

The opening of the file, as written. The whole thing — 700 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Structural Computation

1. Computational Structural Design Philosophy

The Unity of Form and Force

Structure is not an afterthought applied to a completed form. In the computational paradigm, structure is form. The geometry of a building, a bridge, a canopy -- each is a direct expression of the forces acting upon it. When we allow force to generate geometry rather than merely verifying geometry against force, we unlock an entirely different class of architectural expression: one that is simultaneously more efficient, more beautiful, and more materially honest.

This represents a fundamental epistemological shift: from analysis-after-design to analysis-as-design. The former treats structure as a constraint to be checked; the latter treats structure as a generative engine. In computational structural design, the distinction between "architect" and "engineer" dissolves. The designer works directly with force, curvature, material flow, and stress trajectories as primary design media.

Performance-Driven Geometry

Performance-driven geometry emerges when structural performance metrics (stress utilization, deflection, weight, embodied carbon) become the objective functions of a generative process. The designer defines boundary conditions, loads, material palettes, and performance targets. The computation produces geometry. This is not a loss of authorship -- it is an expansion of the design space far beyond what manual intuition can explore.

Key principles of performance-driven geometry:

  • Axial action over bending -- Funicular forms carry load through compression or tension, avoiding costly bending. A catenary cable and an inverted catenary arch are the purest examples.
  • Curvature as stiffness -- A flat plate is structurally weak; a curved shell resists load through membrane action. Double curvature provides bidirectional stiffness. The egg is the canonical example.
  • Material where stress exists -- Topology optimization removes material where stress is absent and concentrates it along principal stress trajectories. The result resembles trabecular bone.
  • Hierarchy and redundancy -- Efficient structures distribute load through hierarchical branching (trees, Gothic vaults, diagrid systems) with multiple load paths for robustness.

Read the full file on GitHub · 700 lines

Files

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.

Changes

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.

  1. 11d ago First seen · 700 lines · 33 tokens per session scan A ca38839e0efc

Subscribe to this mod's changes

structural-computation 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 11,806 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.

Related

Other skills, from other repositories

structural-computation

Finite element analysis fundamentals, form-finding methods, shell and gridshell structures, topology optimization, structural optimization, material-aware computation, and computational structural tools for AEC.

marcinfinitesimal533/Claude-skills-for-Computational-Designers · 33 tokens

proteomics-structural

Load when summarising cross-linking MS (XL-MS) results — intra/inter-protein link split, optional FDR filtering, distance-constraint validation against a per-crosslinker (DSS / BS3 / EDC / DSSO / DSBU) max distance. Skip when raw spectra are the input (run XlinkX / pLink / xiSEARCH first); no XL-MS experiment was…

TianGzlab/OmicsClaw · 88 tokens

cd-calculator

Python calculators for geometry analysis, structural checking, solar calculations, panel optimization, mesh analysis, material estimation, and fabrication cost estimation for AEC computational design.

marcinfinitesimal533/Claude-skills-for-Computational-Designers · 30 tokens

instrument-data-to-allotrope

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…

anthropics/knowledge-work-plugins · 123 tokens

exploratory-data-analysis

Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…

K-Dense-AI/scientific-agent-skills · 83 tokens

matlab

Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.

K-Dense-AI/scientific-agent-skills · 42 tokens