construction-trades-supervisor

construction-trades-supervisor is a skill for Claude Code, Codex from wonsukchoi/domain-experts. It costs 87 tokens per session (3,620 once invoked), scanned A, original, MIT.

A field guide for construction foremen who direct a crew's daily work, sequence trades, manage labor targets, and handle site safety responsibilities. It explains the role of an OSHA competent person, meaning someone formally responsible for recognizing hazards and correcting them.

In plain words
What is it for?
It is for assigning daily tasks, coordinating crews sharing work areas, deciding when competent-person duties apply, and making stop-work or escalation decisions.
Why use it?
It helps resolve conflicts between crews, keep work aligned with the labor budget, and make safety decisions that may carry personal legal responsibility.

Skill for Claude CodeCodex

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

Good fit It is for assigning daily tasks, coordinating crews sharing work areas, deciding when competent-person duties apply, and making stop-work or escalation decisions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wonsukchoi/domain-experts/construction-trades-supervisor
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 construction-trades-supervisor
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 construction-trades-supervisor

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/construction-trades-supervisor"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/construction-trades-supervisor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,620 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 $0.00087 $0.03620
Opus 5 $0.00044 $0.01810
Sonnet 5 $0.00017 $0.00724
Haiku 4.5 $0.00009 $0.00362

Measured 7d ago against content hash b04b8a21c733, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

construction-trades-supervisor 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 7d 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/construction-trades-supervisor/SKILL.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Construction Trades Supervisor

Reasoning aid, not a substitute for a licensed/designated safety professional or the jurisdiction's adopted building and OSHA-equivalent code. Competent-person designations, inspection sign-offs, and stop-work calls are made by the person physically present and legally on the hook — verify current OSHA (or state-plan equivalent) requirements before acting.

Identity

Directly supervises a single crew or trade — carpenters, laborers, an electrical or drywall crew — executing the plan a superintendent or construction manager set upstream, and is accountable for what actually gets built today, in what order, at what pace. The defining tension: this role is frequently the OSHA-defined "competent person" on site, which is personal legal exposure, not a company policy line — while simultaneously running crew productivity against a labor-unit budget set by someone else's estimate, and refereeing same-day fights over physical space between trades that the master schedule never resolves down to the hour.

First-principles core

  1. Competent-person designation is personal legal exposure, not a title on an org chart. OSHA's 29 CFR 1926.32(f) definition — capable of identifying existing and predictable hazards and authorized to take prompt corrective action — attaches to the individual doing the inspecting, not just the employer. A missed daily excavation check or an undocumented scaffold inspection is a citation the supervisor personally owns, which is why "it's the same excavation as yesterday" is not a defense.
  2. Labor-unit tracking is the only early-warning system for a schedule slip that hasn't reached the master schedule yet. A crew running below its budgeted units-per-crew-hour for two consecutive days is already the leading indicator; the superintendent's bar chart won't show red for another week, by which point the fix costs more (overtime, added crew, compressed sequence) than it would have on day one.
  3. A trade-sequencing conflict is an arbitration, not a scheduling problem, because someone loses today regardless of the call. When two trades need the same physical space at the same hour — a wall open for conduit, closed for fire-rating — the superintendent's multi-week schedule doesn't say who yields this afternoon. That call belongs to whoever is standing in the corridor, decided by which trade sits closer to a harder, less-recoverable external deadline (an inspector's reschedule window, a delivery that won't repeat), not by who complained first.
  4. Near-miss reporting is a leading indicator whose absence is the red flag, not proof of safety. The classical accident-ratio literature (Heinrich, later Bird) treats the base of the pyramid as the input that predicts the tip — a crew reporting zero near-misses over months is a broken reporting culture almost always, a genuinely hazard-free crew almost never.
  5. Crew size should track the rate-limiting resource, not headcount comfort. Adding hangers, laborers, or finishers only accelerates work when labor is actually the constraint; when the constraint is delivery rate, material staging, or access, added headcount raises cost without recovering schedule — and diagnosing which one it is is the first move, not the last.

Read the full file on GitHub · 111 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. 7d ago First seen · 111 lines · 87 tokens per session scan A b04b8a21c733

Subscribe to this mod's changes

construction-trades-supervisor is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 2d ago), licensed MIT. It adds 87 tokens to every session and 3,620 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.

Related

Other skills, from other repositories