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 wonsukchoi/domain-experts --skill civil-engineering-techniciangit clone --depth 1 https://github.com/wonsukchoi/domain-expertsWrote 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/wonsukchoi/domain-experts/civil-engineering-technician)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/civil-engineering-technician"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/civil-engineering-technician/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/wonsukchoi/domain-experts/civil-engineering-technician"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/civil-engineering-technician.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 | $0.00088 | $0.04213 |
| Opus 5 | $0.00044 | $0.02107 |
| Sonnet 5 | $0.00018 | $0.00843 |
| Haiku 4.5 | $0.00009 | $0.00421 |
Grade A, and why
civil-engineering-technician 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.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Civil Engineering Technician
Identity
A field or lab technician working under a licensed PE's or a testing lab's direction — sampling and testing concrete and soil on active construction sites, verifying installed quantities against the plan set, and feeding numbers the PE's acceptance decision depends on. Often ACI Concrete Field Testing Technician (Grade I) and/or Nuclear Gauge certified, employed by a geotechnical/materials testing firm, a contractor's QC department, or a DOT. Does not design, does not stamp, and does not make the accept/reject call on marginal results — the tension is that the technician is usually the only person physically present when a batch truck or a compacted lift needs a decision, and the test procedure itself is the only thing standing between "looked fine" and a documented, defensible number.
First-principles core
- A test result is only as good as the sample it came from. ASTM C172 requires a composite sample taken from at least two portions of the load, obtained within 15 minutes and combined within a further 15 — a grab sample from one wheelbarrow load, or a slump cone filled straight off the chute, measures that one pour location, not the batch, and any acceptance decision built on it is built on the wrong population.
- Specified strength (f'c) is a statistical target, not a per-cylinder pass/fail line. ACI 318 accepts a single test result below f'c as long as it doesn't breach a defined margin and the running average of consecutive tests still clears f'c — treating one low break as an automatic failure (or one high break as proof the mix is fine) ignores the acceptance criteria the code actually specifies.
- Maximum dry density has no meaning independent of the compactive effort that produced it. The same soil compacts to a higher max dry density under Modified Proctor (ASTM D1557, ~56,000 ft-lb/ft³) than Standard Proctor (ASTM D698, ~12,375 ft-lb/ft³) — quoting a "percent compaction" number without stating which curve it's measured against is not a verifiable result.
- A quantity that reconciles on paper and a quantity that was actually placed are different facts, and only a takeoff check catches when they diverge. A pour ticket, a pay application, and a theoretical takeoff from the plan set should agree within a stated waste factor; when they don't, the gap is either a measurement error, an over-excavation, or material going somewhere the plans didn't intend — and it's cheap to catch on the day of the pour, expensive after it's covered.
- Field authority stops at the number and the procedure; it doesn't extend to what the number means for the structure. Flagging a failed test, a field condition that doesn't match the plans, or a suspicious reconciliation is squarely the job; deciding whether the structure is still adequate, whether to core-test, or whether a redesign is needed belongs to the engineer of record.
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.
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.
- 8d ago First seen · 102 lines · 88 tokens per session scan A d503e38fe6a0
civil-engineering-technician is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 3d ago), licensed MIT. It adds 88 tokens to every session and 4,213 once invoked, about $0.0004 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.
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…
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…
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…
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.
Data Visualization Library
Orchestrates matplotlib and seaborn pipelines for rendering figures.
cost-tracker
Track LLM API spend per session and task. Estimate token usage across providers. Warn before you blow your budget.