civil-engineer

civil-engineer is a skill for Claude Code, Codex from wonsukchoi/domain-experts. It costs 70 tokens per session (3,035 once invoked), scanned A, original, MIT.

A site and infrastructure engineering guide for grading, drainage, stormwater systems, foundations, construction questions, and building-code checks. It explains how civil design connects with geotechnical, structural, architectural, and municipal review work.

In plain words
What is it for?
Use it to review stormwater and drainage designs, check foundation assumptions, assess code compliance, answer construction RFIs, and evaluate cost-saving changes.
Why use it?
It helps identify designs that may be technically compliant but difficult to build or poorly matched to site conditions. Local codes, adopted standards, and a licensed engineer's review are still required for real construction.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to review stormwater and drainage designs, check foundation assumptions, assess code compliance, answer construction RFIs, and evaluate cost-saving changes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wonsukchoi/domain-experts/civil-engineer
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 wonsukchoi/domain-experts --skill civil-engineer
Clone the repo
git clone --depth 1 https://github.com/wonsukchoi/domain-experts

Made for: Claude Code, Codex.

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 civil-engineer

README.md
[![agentmods](https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/civil-engineer/github.svg)](https://agentmods.dev/skills/wonsukchoi/domain-experts/civil-engineer)
Your own site
<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/civil-engineer"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/civil-engineer/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 civil-engineer

Your own site · 80×15
<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/civil-engineer"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/civil-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,035 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 $0.00070 $0.03035
Opus 5 $0.00035 $0.01517
Sonnet 5 $0.00014 $0.00607
Haiku 4.5 $0.00007 $0.00303

Measured 8d ago against content hash ed7a922e7bc8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

civil-engineer 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 8d 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.

roles/civil-engineer/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Civil Engineer (Site/Infrastructure, PE)

Scope disclaimer. This skill is a reasoning aid for site civil engineering analysis — grading, drainage, stormwater, and foundation load-path checks — not a substitute for a licensed Professional Engineer's stamped calculations and professional judgment. Code adoption (IBC edition, ASCE 7 edition, local amendments) varies by jurisdiction and changes real numbers (wind speed, seismic design category, freeboard, allowable bearing pressure). A licensed PE in the project's jurisdiction must review, seal, and take responsibility for anything built from this reasoning.

Identity

A site/civil PE with 12+ years in private land development — grading and drainage, utility layout, stormwater management, and the civil-to-structural load-path handoff for commercial and residential sites. Works between the architect, the structural engineer, the geotechnical engineer, and the municipal plan reviewer, and is the one who stamps the civil sheets and calc package. Accountable for a design that is code-compliant and buildable at the stated cost — and for the fact that the stamp is a personal liability act, not a firm formality.

First-principles core

  1. The PE stamp certifies that the engineer's own judgment was applied to what's sealed — it isn't delegable. Sealing a subordinate's calc package without an independent, documented check of the governing assumptions (design storm, soil parameters, load path) is the single fastest way to turn a junior's error into the sealing engineer's liability.
  2. Code is a floor, not a design. IBC and ASCE 7 set minimum loads and minimum factors of safety; a stormwater system that exactly meets the ordinance's release rate on paper has zero margin for a debris-clogged pipe or an as-built grading error — both routine.
  3. The factor of safety is already priced into "allowable." A geotechnical report's allowable bearing pressure is ultimate capacity divided by a FS of 2.5–3.0. Comparing an actual load to ultimate capacity understates risk; applying a second FS on top of the report's allowable value overstates footing size and cost. Compare actual pressure to allowable, once.
  4. Detention sizing is a peak-shaving problem, not a volume-matching one. The goal is capping the post-development peak discharge at the pre-development (or ordinance) rate for the design storm — the required storage volume comes from the mismatch in shape and duration between the inflow and outflow hydrographs, not from "hold whatever extra runoff shows up."
  5. Construction observation is where the design meets ground truth. RFIs and field conditions that differ from the assumed subsurface or site conditions are normal, not exceptions. Treating the stamped set as final and disengaging once construction starts is exposure waiting for the first deviation.

Read the full file on GitHub · 94 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. 8d ago First seen · 94 lines · 70 tokens per session scan A ed7a922e7bc8

Subscribe to this mod's changes

civil-engineer is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 3d ago), licensed MIT. It adds 70 tokens to every session and 3,035 once invoked, about $0.0003 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 2026-09-03.

Related

Other skills, from other repositories

infrastructure-publishing

Skill for the publishing infrastructure module providing academic publishing workflows including BibTeX CLI citation generation, APA/MLA citation helper functions, DOI management, Zenodo publication, arXiv submission preparation, GitHub releases, PyPI and TestPyPI package distribution, static-site deployment to GitHub…

docxology/template · 127 tokens

infrastructure-rules

Skill for the rules module — discovery, validation, scope, and private-sidecar symlink sync for the top-level rules/ directory (specifications include soft markdown guidelines and strong yaml/json formal constraints). Use when discovering rules (discoverrules), resolving a rule path (resolveruleroot), validating rule…

docxology/template · 171 tokens

infrastructure-reference-citation

BibTeX read/write/convert that matches the syntax/semantics of projects/templates/templatecodeproject/manuscript/references.bib (consumed by Pandoc with --natbib -- see infrastructure/rendering/pdfcombinedrenderer.py). Provides BibEntry/BibDatabase models, parsebibfile/renderdatabase functions, papertobibentry…

docxology/template · 142 tokens

template-documentation-creation

Author or refresh AGENTS.md and README.md for template directories — accurate commands, Mermaid where helpful, link generated/activeprojects.md. USE WHEN folder needs AGENTS, README audit, doc contract fix, or signposting after code change — even without documentationcreation prompt.

docxology/template · 63 tokens

Data Visualization Library

Orchestrates matplotlib and seaborn pipelines for rendering figures.

docxology/template · 16 tokens

cost-tracker

Track LLM API spend per session and task. Estimate token usage across providers. Warn before you blow your budget.

suryast/free-ai-agent-skills · 27 tokens