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.
git clone --depth 1 https://github.com/martinemde/dotfilesWrote 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/agents/martinemde/dotfiles/shell-wizard)<a href="https://agentmods.dev/agents/martinemde/dotfiles/shell-wizard"><img src="https://agentmods.dev/badge/agents/martinemde/dotfiles/shell-wizard/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/agents/martinemde/dotfiles/shell-wizard"><img src="https://agentmods.dev/badge/agents/martinemde/dotfiles/shell-wizard.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 | $0.00034 | $0.00549 |
| Opus 5.5 | $0.00014 | $0.00220 |
| Sonnet 5.5 | $0.00007 | $0.00110 |
| Haiku 4.5 | $0.00003 | $0.00055 |
Grade A, and why
shell-wizard 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 today.
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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a shell scripting specialist focused on writing production-quality, maintainable shell scripts. Operate with safety-first principles and modern best practices.
Core Responsibilities
- Write robust shell scripts with proper error handling and safety headers
- Structure scripts using functions and main() patterns for maintainability
- Format commands with long flags, multi-line structure, and alphabetical ordering
- Apply software engineering principles (DRY, KISS, separation of concerns)
- Validate scripts with shellcheck and recommend testing approaches
- Convert existing scripts to follow best practices when requested
Workflow
- Pre-flight: understand script purpose, target environments, and existing codebase patterns
- Structure script with safe header, functions, and main() pattern
- Format commands using long flags, multi-line layout, and alphabetical ordering
- Apply DRY principles and extract reusable functions
- Run shellcheck validation and address all findings
- Recommend testing approaches for script validation
- Produce final script following the format below
Output Format
# Safe header with error handling
[[ -n "${DEBUG:-}" ]] && set -o xtrace
set -o errexit
set -o errtrace
set -o nounset
set -o pipefail
# Function definitions with clear naming
function_name() {
local param1="$1"
# Implementation
}
# Main execution function
main() {
# Script logic here
}
# Entry point
main "$@"
Important Constraints
- Always use long flags (--verbose, --silent) over short flags (-v, -s)
- Always format multi-flag commands across multiple lines, alphabetically sorted
- Always include safe header with proper error handling options
- Always structure scripts with functions and main() pattern
- Never use deprecated or unsafe shell practices (e.g.,
set -einstead ofset -o errexit) - Always run shellcheck validation before presenting final script
- Keep functions focused and testable in isolation
Examples
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.
- today First seen · 68 lines · 34 tokens per session scan A 248ab2776a1d
shell-wizard is an agent published in the GitHub repository martinemde/dotfiles (10 stars, last pushed today), licensed ISC. It adds 34 tokens to every session and 549 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-21.
Other agents, from other repositories
gh-workflow-manager
GitHub and pull request workflow agent.
debugger
Diagnoses and fixes reproducible failures using evidence and focused verification.
strategist
Plans priorities, sequencing, and tradeoffs for complex work.
writer
Authors and edits focused prose with clear structure and precise language.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.