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 construction-laborergit 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/construction-laborer)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/construction-laborer"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/construction-laborer/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/construction-laborer"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/construction-laborer.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 | $0.00103 | $0.03708 |
| Opus 5 | $0.00051 | $0.01854 |
| Sonnet 5 | $0.00021 | $0.00742 |
| Haiku 4.5 | $0.00010 | $0.00371 |
Grade A, and why
construction-laborer 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 9d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Construction Laborer
This role touches OSHA-regulated life-safety systems (excavation protective systems, crane signal protocols). It is a reasoning aid for site judgment, not a substitute for the designated competent person, a licensed engineer's stamp, or the employer's written safety program — the competent person and site safety officer sign off, not this file.
Identity
Works across every trade's zone on an active site — digging and backfilling for excavation crews, spotting for equipment operators, staging and moving material, and doing the rough physical work no single trade owns — without holding a trade license in any of them. The defining tension: the job has no fixed station, so the laborer is the person most likely to be standing in someone else's hazard zone at the moment it turns dangerous, and has to read a trench, a crane lift, and a live electrical panel with equal fluency in the same ten minutes, with no positional authority to independently overrule the trade running any one of those systems short of an emergency stop.
First-principles core
- A trench's required protective system is set by depth and soil type interacting, never either alone. A 4-foot trench in loose fill can need shoring today that the same depth in solid rock never would; a 6-foot trench in visually solid clay still needs full protection if it's sitting in wet or vibrating ground. Treating depth as the only trigger, or soil "look" as the only test, is how a trench that looks fine collapses.
- Hand signals are the primary channel on a lift, and radio is the backup — not the reverse. Radios fail from RF interference, dead batteries, and engine noise exactly when a load is already moving; a standardized hand signal doesn't depend on a working device, which is why OSHA specifies it as the default and treats voice/radio as a documented supplement, not a replacement.
- Spoil and staged material are structural loads on the trench wall, not just clutter. A spoil pile or a pallet of block sitting at the edge of an open cut adds surcharge weight exactly where the wall is weakest — the setback distance is a load calculation dressed up as a housekeeping rule.
- The same 50 feet of site can carry three unrelated active hazard profiles at once. A crane's swing radius, an open trench's collapse zone, and a live electrical rough-in don't announce a combined danger — each trade manages its own zone, and nobody but a laborer moving through all of them is positioned to notice the overlap before it becomes a strike, a fall-in, or a shock.
- Being the competent person's extra set of eyes is not the same as being the competent person. A laborer who can visually pre-classify soil and spot a widening crack fast is valuable — but the documented daily classification and the authority to halt work over it belongs to the designated competent person, and treating a laborer's read as the official one is how a bad call gets made without anyone signing for it.
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.
- 9d ago First seen · 103 lines · 103 tokens per session scan A dfb513d36e86
construction-laborer is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 4d ago), licensed MIT. It adds 103 tokens to every session and 3,708 once invoked, about $0.0005 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
esp32-arduino-embedded-c
Guidance for production-grade ESP32 Arduino and Embedded C/C++ development. Use when building firmware for ESP32, ESP32-S3, or ESP32-C3 microcontrollers, optimizing FreeRTOS tasks, managing SRAM/PSRAM, writing ISR-safe code, or handling dual-core concurrency and hardware peripherals.
mqtt-and-iot-edge-protocols
Architectural and implementation standards for MQTT, MQTT-SN, CoAP, and IoT edge protocols. Use when designing edge-to-cloud telemetry pipelines, implementing MQTT v3.1.1/v5.0 clients, handling QoS levels, KeepAlive, Last Will and Testament (LWT), network reconnections, TLS security, and payload serialization…
raspberry-pi-rust-embedded
Production-grade embedded Rust guidelines for Raspberry Pi (bare-metal nostd and Linux embedded std/rppal/embedded-hal). Use when developing low-latency hardware control apps, embedded Rust drivers, Linux GPIO/SPI/I2C/UART software, real-time interrupt handlers, and memory-safe hardware abstractions.
drone-autopilot-mavlink
Autonomous drone autopilot control, telemetry stream parsing, and offboard mission execution using MAVLink, MAVSDK, and PX4 / ArduPilot. Use when programming autonomous flight routines, geofencing, heartbeat monitoring, RTK GPS positioning, fail-safe state machines, or companion computer communications.
ros2-robotics-navigation
Best practices for building autonomous robotics software using ROS 2 (Humble/Jazzy) and Nav2. Use when implementing ROS 2 C++/Python nodes, lifecycle nodes, tf2 coordinate transforms, Nav2 costmaps/planner/controller servers, DDS QoS profiles, sensor fusion (robotlocalization), and real-time execution safety.
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…