Borrowing it
Nothing to install: this file belongs to ScottDuncanAI/industrial-ai-troubleshooting-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ScottDuncanAI/industrial-ai-troubleshooting-agent/main/.claude/commands/setup.mdgit clone --depth 1 https://github.com/ScottDuncanAI/industrial-ai-troubleshooting-agentWrote 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/commands/scottduncanai/industrial-ai-troubleshooting-agent/setup)<a href="https://agentmods.dev/commands/scottduncanai/industrial-ai-troubleshooting-agent/setup"><img src="https://agentmods.dev/badge/commands/scottduncanai/industrial-ai-troubleshooting-agent/setup/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/commands/scottduncanai/industrial-ai-troubleshooting-agent/setup"><img src="https://agentmods.dev/badge/commands/scottduncanai/industrial-ai-troubleshooting-agent/setup.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 | $0.00000 | $0.01432 |
| Opus 5 | $0.00000 | $0.00716 |
| Sonnet 5 | $0.00000 | $0.00286 |
| Haiku 4.5 | $0.00000 | $0.00143 |
Grade B, and why
setup scanned grade B with 1 finding 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 10d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
installs), tell the user to install it (e.g. `sudo apt install python3-venv`) and run `/setup` How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
First-Time Setup
Run all setup steps so the user can start using the Boiler Historian project. The user may have no coding experience — do not ask them to run commands or edit files. Handle everything yourself and explain what you're doing in plain language as you go.
Steps
1. Check Python
Verify Python 3.11+ is installed. Try both python and python3 — on macOS the
bare python command usually does not exist, and Python is invoked as python3, so do
not conclude Python is missing until both have failed:
python --version
python3 --version
Use whichever command reports version 3.11 or newer. Remember which command worked (call it the system Python below) — you will use that same command to create the virtual environment in Step 2.
Only if neither python nor python3 reports 3.11+ (both are missing, or both are
below 3.11), stop and tell the user:
- They need to install Python 3.11 or newer
- Direct them to https://www.python.org/downloads/
- On Windows, remind them to check "Add Python to PATH" during installation
- On macOS, they can confirm their version any time with
python3 --version - Ask them to run
/setupagain after installing Python
2. Create a project-local virtual environment and install dependencies
Install all dependencies into a virtual environment (venv) inside the project folder rather
than into the user's global Python. This keeps everything self-contained: the packages live in a
.venv/ folder in the project (already git-ignored), nothing is added to the global Python
installation, and there are no version clashes with other software on the user's machine.
First, create the virtual environment in the project root, using the system Python
command that worked in Step 1 (python or python3 — on macOS this is almost always
python3):
python3 -m venv .venv
(Substitute python if that was the command that reported 3.11+ in Step 1.)
Then install the dependencies into the venv, using the venv's own Python. The path to the venv's Python depends on the operating system:
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.
- 10d ago First seen · 142 lines · 0 tokens per session scan B 4e7ebc61fd5a
setup is a command published in the GitHub repository ScottDuncanAI/industrial-ai-troubleshooting-agent (59 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,432 tokens. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.