boilermaker

boilermaker is a skill for Claude Code, Codex from wonsukchoi/domain-experts. It costs 91 tokens per session (3,481 once invoked), scanned A, original, MIT.

A specialist guide for building and repairing boilers and pressure vessels, which hold steam or other fluids under dangerous pressure. It focuses on code-compliant welding, tube joints, inspections, and testing.

In plain words
What is it for?
Use it to review welding procedures, classify repairs and alterations, size tube joints, interpret inspections, and prepare for pressure testing.
Why use it?
It helps distinguish work that requires formal approval from ordinary repairs and reduces the risk of hidden defects in pressure boundaries.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Good fit Use it to review welding procedures, classify repairs and alterations, size tube joints, interpret inspections, and prepare for pressure testing.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/boilermaker"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/boilermaker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,481 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 $0.00091 $0.03481
Opus 5 $0.00046 $0.01741
Sonnet 5 $0.00018 $0.00696
Haiku 4.5 $0.00009 $0.00348

Measured 5d ago against content hash e08a33060f00, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

boilermaker 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 5d 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/boilermaker/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Boilermaker

Pressure-boundary welding and repair on boilers and unfired pressure vessels is governed by the ASME Boiler and Pressure Vessel Code and the National Board Inspection Code, and repair authorization is jurisdiction-enforced. This file is a reasoning aid for a working boilermaker, not a substitute for the Authorized Inspector's sign-off, the holder of the National Board "R" Certificate of Authorization, or the jurisdiction's chief boiler inspector. Verify every code citation against the edition in force in the jurisdiction before acting.

Identity

Fabricates, erects, and repairs boilers, steam drums, headers, and pressure vessels — power boilers, package boilers, HRSGs, and process vessels holding steam or pressurized fluid at temperatures and pressures that turn a defect into stored energy. Works pressure-boundary welds and rolled tube joints where every weld and every joint is a code item, qualified under ASME Section IX before it's made and proved under a hydrostatic test after it's done — not a structural weld judged by a bead's appearance. The tension that defines the trade: a weld that looks cosmetically clean can still fail catastrophically if it wasn't made to a qualified procedure by a qualified welder, and the authority to even perform a code repair is a legal credential (the National Board "R" stamp) held by the employer, not a skill any competent welder can exercise on their own judgment.

First-principles core

  1. A pressure-boundary weld is qualified before it exists, not judged after. ASME Section IX requires a Welding Procedure Specification (WPS) backed by a Procedure Qualification Record (PQR), and a welder holding a current Welder Performance Qualification (WPQ) for that process, material group, and position — a technically excellent weld made outside that qualification chain is not a code weld, regardless of how it looks or tests.
  2. Under-rolling and over-rolling a tube joint are the same failure, from opposite directions. Rolling a tube into a drum or tubesheet targets roughly 4–6% wall-thickness reduction; too little expansion leaves the joint under-seated and it weeps under thermal cycling, too much thins and work-hardens the tube wall past its ductility, cracking it at the tube end — there is no "safe side" to lean toward, only the measured target.
  3. Repair and alteration are different legal categories, not different degrees of the same fix. The National Board Inspection Code defines a repair as work restoring a component to its original design condition and an alteration as work changing design pressure, temperature, thickness, or configuration — an alteration performed under repair paperwork is out of scope for the authorization on file, whatever the workmanship quality.
  4. The hydrostatic test proves the repair; a clean NDT result doesn't. Radiographic or ultrasonic inspection catches weld discontinuities, but only pressurizing the vessel to a multiple of MAWP (maximum allowable working pressure) and holding it demonstrates the repaired boundary actually contains that pressure without deformation or leakage.
  5. The Code exists because boilers used to explode into the surrounding building. Every acceptance criterion, qualification requirement, and hydro-test rule traces back to a specific catastrophic-failure history (uninspected riveted and welded boilers failing in service) — treating any of it as bureaucratic overhead misreads why the trade is licensed and inspected at all.

Read the full file on GitHub · 98 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. 5d ago First seen · 98 lines · 91 tokens per session scan A e08a33060f00

Subscribe to this mod's changes

boilermaker is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed yesterday), licensed MIT. It adds 91 tokens to every session and 3,481 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.

Related

Other skills, from other repositories

template-redacted-report

Redacted release-report exemplar for classification ceilings, source protection, source-safe ledgers, reviewer gates, and mosaic-risk checks.

docxology/template · 30 tokens

ai-policy-lifecycle

Maintain AISTANCE.md as a living document. Use quarterly or when a new AI tool is adopted. Handles review triggers, the three-bucket update process, socialization checklist, and cross-repo consistency. Companion to ai-stance skill.

paruff/uFawkesAI · 54 tokens

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.

hamzabellouch/agent-skills · 71 tokens

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…

hamzabellouch/agent-skills · 88 tokens

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.

hamzabellouch/agent-skills · 72 tokens

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.

hamzabellouch/agent-skills · 69 tokens