dx

dx is a skill for Claude Code from mthines/agent-skills. It costs 155 tokens per session (1,444 once invoked), scanned A, original, MIT.

A developer-experience review for command-line tools, shell scripts, build tools, and automation.

In plain words
What is it for?
Use it to review a command-line program, shell script, build task, or automation workflow. It identifies the tool type, reads the relevant code, and gives specific improvement advice.
Why use it?
It finds confusing behavior, poor error handling, and design choices that make developer tools harder to use or combine with other commands. The review is based on established command-line guidelines.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Part of the mthines-agent-skills plugin — 54 skills, 4 agents shipped together

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.

agentmods
npx agentmods add skills/mthines/agent-skills/dx
Any agent
npx skills add mthines/agent-skills --skill dx
Clone the repo
git clone --depth 1 https://github.com/mthines/agent-skills

Made for: Claude Code.

Or install mthines-agent-skills, the plugin that ships this one along with the rest of its 54 skills, 4 agents.

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 dx

README.md
[![agentmods](https://agentmods.dev/badge/skills/mthines/agent-skills/dx.svg)](https://agentmods.dev/skills/mthines/agent-skills/dx)
Your own site
<a href="https://agentmods.dev/skills/mthines/agent-skills/dx"><img src="https://agentmods.dev/badge/skills/mthines/agent-skills/dx.svg" alt="Measured on agentmods" height="20"></a>
Per session 155 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,444 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00155 $0.01444
Opus 5 $0.00077 $0.00722
Sonnet 5 $0.00031 $0.00289
Haiku 4.5 $0.00015 $0.00144

Measured 6d ago against content hash 2f64636e0492, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

dx 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 6d 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.

skills/quality/dx/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DX Review Skill

You are an expert Developer Experience (DX) reviewer specializing in CLI tools, shell scripts, developer tooling, and automation. Your role is to analyze tool code and provide actionable, specific feedback grounded in established CLI design principles, composability standards, and developer ergonomics.

Invocation

When triggered, follow this workflow:

Phase 1: Context Discovery

  1. Identify target: Determine which files/components to review from:
    • User's explicit request ("review this CLI")
    • Recent git changes (git diff --name-only HEAD~1 for changed tool files)
    • Current file context if invoked inline
  2. Detect tool type: Determine if reviewing:
    • Compiled CLI: Go (Cobra/cli), Rust (clap), Deno/Node (oclif), etc.
    • Shell script: Bash, Zsh, Fish, POSIX sh
    • Build/task tool: Makefile, Taskfile, Justfile, npm scripts
    • Hybrid: CLI with shell integration, plugin systems, etc.
    • If ambiguous, ask the user.
  3. Read the code: Read all target files completely. Do not review code you haven't read.

Phase 2: Analysis

Load relevant rule files from rules/ based on what the code contains:

Code Contains Load Rule File
Any CLI/tool code rules/core-principles.md (always)
Help text, usage strings, --help rules/help-and-documentation.md
Console output, colors, formatting rules/output-and-formatting.md
Error handling, exit codes, try/catch rules/error-handling.md
Flags, arguments, option parsing rules/arguments-and-flags.md
Config files, env vars, dotfiles rules/configuration.md
Prompts, TTY detection, interactive UI rules/interactivity.md
Pipes, stdin/stdout, signals, scripting rules/composability.md
Shell scripts (bash, zsh, sh) rules/shell-scripting.md
Test files, test utils, CI config rules/testing.md
Install scripts, packaging, releases rules/distribution.md

Analyze the code against each loaded rule file. For every finding:

  • Identify the specific line(s) in the code
  • Name the violated principle (e.g., "clig.dev: Error Handling", "12 Factor CLI: #3 Stderr")
  • Explain why it matters for the developer using the tool
  • Provide a concrete fix with code

Read the full file on GitHub · 128 lines

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. 6d ago First seen · 128 lines · 155 tokens per session scan A 2f64636e0492

Subscribe to this mod's changes

dx is a skill published in the GitHub repository mthines/agent-skills (12 stars, last pushed yesterday), licensed MIT. It adds 155 tokens to every session and 1,444 once invoked, about $0.0008 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 2026-08-31.

Related

Other skills, from other repositories

life-design

Walk you through the Stanford Designing Your Life method and write your Personal Life Design Blueprint — three Odyssey plans and the prototypes to test them.

coolTheWorld/evolution-skills · 30 tokens

prompt-optimizer

Analyze a draft prompt, diagnose gaps, match it to relevant skills already in this catalog, and output a ready-to-paste improved prompt — advisory only, never executes the task itself. Use when the user says "optimize this prompt", "improve my prompt", "how should I prompt for X", or pastes a draft prompt asking for…

shennawardana23/skillme · 94 tokens

strategic-compact

Use when deciding whether to manually compact conversation context now versus later — at a phase boundary (research done, plan written, milestone shipped), before switching to an unrelated task, or when responses feel slower/less coherent from context pressure. Trigger phrases include "should I compact now", "context…

shennawardana23/skillme · 103 tokens

stay-within-limits

Use when long-running or parallel agent work must respect 5-hour and weekly usage limits by checking usage between waves, pausing near the cap, and resuming only when the window is clear.

BuilderIO/skills · 45 tokens

obsidian-bases

Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.

kepano/obsidian-skills · 63 tokens

find-journalists

Build, refine, dedupe, and enrich small fit-checked journalist lists for newsjack campaigns. Uses the newsjack CLI (preferred) or the medialyst MCP for news search and journalist enrichment, and falls back to a best-effort local mode with no verified contacts; the agent owns how returned data is organized.

elvisun/newsjack · 69 tokens