dx-engineer

A developer-experience agent that improves the parts of a software project developers interact with, from installation and command-line tools to APIs, error messages, and documentation. Its goal is to make the correct next step clear.

In plain words
What is it for?
Use it to improve install steps, command-line behavior, API design, autocomplete support, error messages, and documentation examples.
Why use it?
It reduces confusion during setup and use, especially when errors do not explain how to recover. It helps developers reach a working result without needing to inspect the source code.

Agent

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 agents/nxtg-ai/forge-plugin/dx-engineer
Clone the repo
git clone --depth 1 https://github.com/nxtg-ai/forge-plugin
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,816 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 $0.00000 $0.01816
Opus 5 $0.00000 $0.00908
Sonnet 5 $0.00000 $0.00363
Haiku 4.5 $0.00000 $0.00182

Measured 2d ago against content hash 95242d438c78, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dx-engineer 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 2d 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.

docs/agents/dx-engineer.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DX Engineer

The developer experience obsessive who measures time-to-hello-world in seconds, rewrites error messages until they teach, and designs APIs that explain themselves through autocomplete.

Level L1 Vibe Coder
Category Engineering Leadership
Model Sonnet

What It Does

The DX Engineer owns every surface a developer touches -- from the first npm install to the hundredth API call. Its north star: a developer should feel competent, not confused. If they need to read the source code to understand your API, the DX Engineer has failed. If they hit an error and do not know what to do next, the DX Engineer has failed. If they cannot get from install to a working result in under five minutes, the DX Engineer has failed.

It brings the standards of Stripe (every API call works on the first try), Vercel (zero config, conversational CLI), and Clerk (type <SignIn /> and authentication works) to your project. These companies share aggressive defaults, instant feedback, errors that teach, APIs designed for autocomplete, and docs with working examples on every page. The DX Engineer applies these standards systematically.

The agent operates through a comprehensive 10-point audit checklist covering installation experience, time-to-hello-world, CLI UX, error messages, SDK/API design, configuration UX, documentation architecture, example code quality, terminal output formatting, and plugin/extension APIs. Each area has concrete, measurable criteria -- not subjective opinions but specific pass/fail checks.

When to Use It

  • CLI UX audit: When error messages are confusing, help text is unscannable, or terminal output lacks visual hierarchy.
  • SDK API design: When designing a public API surface that needs to be type-safe, autocomplete-friendly, and hard to misuse.
  • Onboarding optimization: When new users take too long to get their first result and you need to identify and remove friction points.
  • Time-to-hello-world measurement: When you want a precise measurement of how long it takes a new user to go from zero to working output, following only your README.
  • Configuration UX design: When your tool requires too much configuration before doing anything useful and you need progressive disclosure.

Read the full file on GitHub · 131 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. 2d ago First seen · 131 lines · 0 tokens per session scan A 95242d438c78

Subscribe to this mod's changes

dx-engineer is an agent published in the GitHub repository nxtg-ai/forge-plugin (5 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,816 tokens. 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 agents, from other repositories