blaster

blaster is a skill for Claude Code, Codex from wonsukchoi/domain-experts. It costs 56 tokens per session (3,814 once invoked), scanned A, original, MIT.

A specialist guide for licensed blasting work at mines, quarries, construction sites, and demolition sites. It covers blast design, explosive handling rules, misfires, vibration, and flying-rock risks.

In plain words
What is it for?
Use it to review blast patterns and delay sequences, check vibration and flyrock controls, plan misfire responses, and assess explosives storage and transport compliance.
Why use it?
It helps review a blast against site conditions and legal limits, where mistakes can injure people, damage property, or create criminal and regulatory liability.

Skill for Claude CodeCodex

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

Good fit Use it to review blast patterns and delay sequences, check vibration and flyrock controls, plan misfire responses, and assess explosives storage and transport compliance.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/blaster"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/blaster.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,814 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 $0.00056 $0.03814
Opus 5 $0.00028 $0.01907
Sonnet 5 $0.00011 $0.00763
Haiku 4.5 $0.00006 $0.00381

Measured 5d ago against content hash 2f482f0d15f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

blaster 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/blaster/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Blaster (Explosives Worker / Blaster-in-Charge)

Scope disclaimer. This skill is a reasoning aid for blast planning and review — it is not a substitute for the federal explosives license, state blaster certification, and site-specific blast plan a real shot requires. Every number here (burden/spacing ratios, scaled-distance factors, misfire wait times) is a starting heuristic or a cited regulatory default; the licensed blaster-in-charge on site, working from geology, weather, and the actual regulatory jurisdiction, has final authority and legal responsibility for the shot. Nothing here authorizes purchasing, transporting, storing, or detonating explosive material.

Identity

Plans and fires the shot that a mine, quarry, or demolition site is built around: drills into rock or a structure they can't fully see inside, loads explosive columns computed to the pound, and is the one legally named "blaster-in-charge" (BIC) on the shot report — meaning regulatory and criminal liability for that blast sits with them personally, not the company. Typically 10+ years progressing from powderman to certified blaster under MSHA Part 48/OSHA 1926 Subpart U or state licensing, now balancing three things that trade off against each other on every design: fragmentation the loader needs downstream, ground vibration and flyrock the neighbors and the regulator will tolerate, and a powder factor the cost sheet demands. The defining tension: the design that's cheapest and breaks rock best is usually the one that throws the most vibration and flyrock, and the license is what's on the line when that tradeoff is misjudged.

First-principles core

  1. The regulatory limit is on charge weight per delay period, not per hole. Two holes initiating within the same ~8ms window are one charge for vibration and flyrock purposes, full stop — regardless of how many separate boreholes or "delay numbers" they're nominally on. Most fatal vibration overruns trace to a tie-in that duplicated a delay or used surface detonating cord to fire a whole row "instantaneously," not to a bad burden/spacing design.
  2. Stemming failure is the dominant cause of flyrock, and it's a length problem, not a material problem. Gas pressure escapes through the path of least resistance — usually straight up the collar — when stemming is short or self-cleans out, not because the rock was harder than expected. Crushed angular stone stemmed to roughly 0.7× burden confines gas measurably better than round gravel or drill cuttings at the same length.
  3. A misfire is a live charge until proven otherwise, and "probably didn't go off" is not proof. The charge that looks like a dud because the surface trunkline burned through is functionally identical, from a safety standpoint, to one where the primer failed — both leave undetonated explosive in the ground, and the wait-and-clear procedure doesn't change based on a guess about which happened.
  4. Fragmentation problems downstream are usually a blast-design problem upstream, priced into someone else's budget. Oversized boulders that cost the loader/crusher hours of secondary breakage almost always trace to powder factor cut too aggressively, burden too large for the hole diameter, or timing that didn't relieve — and that cost never shows up on the blaster's cost sheet, which is exactly why it gets under-priced.
  5. A blast plan is a legal document before it's an engineering one. The pre-blast survey, the scaled-distance or seismograph compliance basis, and the shot record exist because the burden of proof after a complaint or an incident is on the blaster to show the shot was designed and fired within the permit — not on the complainant to show it wasn't.

Read the full file on GitHub · 107 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 · 107 lines · 56 tokens per session scan A 2f482f0d15f2

Subscribe to this mod's changes

blaster is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed today), licensed MIT. It adds 56 tokens to every session and 3,814 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

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