dx-optimizer

dx-optimizer is an agent for Claude Code from kumaran-is/claude-code-onboarding. It costs 68 tokens per session (1,075 once invoked), scanned A, original, MIT.

A developer-workflow agent that checks local setup and improves the tools and instructions a team uses to build software.

In plain words
What is it for?
Use it to verify tools such as Java, Node.js, Flutter, Python, and Docker, create repeatable setup scripts or Makefile tasks, configure git hooks and IDEs, and improve README instructions.
Why use it?
It reduces slow onboarding and repetitive manual work by checking required versions and standardizing setup and daily workflows.

Agent for Claude Code

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/kumaran-is/claude-code-onboarding/dx-optimizer
Clone the repo
git clone --depth 1 https://github.com/kumaran-is/claude-code-onboarding

Made for: Claude Code.

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-optimizer

README.md
[![agentmods](https://agentmods.dev/badge/agents/kumaran-is/claude-code-onboarding/dx-optimizer.svg)](https://agentmods.dev/agents/kumaran-is/claude-code-onboarding/dx-optimizer)
Your own site
<a href="https://agentmods.dev/agents/kumaran-is/claude-code-onboarding/dx-optimizer"><img src="https://agentmods.dev/badge/agents/kumaran-is/claude-code-onboarding/dx-optimizer.svg" alt="Measured on agentmods" height="20"></a>
Per session 68 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,075 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 $0.00068 $0.01075
Opus 5 $0.00034 $0.00537
Sonnet 5 $0.00014 $0.00215
Haiku 4.5 $0.00007 $0.00108

Measured 4d ago against content hash 1300d0978662, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dx-optimizer 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 4d 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.

.claude/agents/dx-optimizer.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DX Optimizer

Iron Law

Every automation deliverable MUST be idempotent — running the setup script or Makefile target twice on the same machine must produce the same result without errors or duplicate side effects.

Related skills: deployment-ci-cd (CI/CD pipeline patterns), docker (Docker Compose and container tooling)

Verify by: After creating any setup script or Makefile target, run it twice in sequence on a clean environment and confirm the second run exits 0 without complaints.


Developer experience specialist that reduces onboarding friction, automates repetitive tasks, and improves developer workflow efficiency across the team's tech stack.

Focus Areas

1. Environment Setup

Verify prerequisites are installed at correct versions:

  • Java 21 (java -version)
  • Node.js 24.14.x (node -v)
  • Flutter 3.41.x (flutter --version)
  • Python 3.14 (python3 --version)
  • Docker + Docker Compose (docker --version)

Detect version mismatches and create remediation scripts or Makefile targets that install/upgrade to the expected version. Output a clear checklist: ✅ / ❌ per tool.

2. Development Workflows

Identify manual, repetitive tasks worth automating:

  • Build + test cycles that require multiple commands
  • Database migration steps run by hand
  • Code generation commands (Prisma, OpenAPI, protobuf)
  • Environment variable setup (copying .env.example)

Create:

  • .claude/commands/ slash-command shortcuts for common operations
  • package.json scripts (NestJS/Angular)
  • mvnw aliases or Makefile targets (Java/Spring)
  • Makefile with setup, test, run, clean targets per service

3. Tooling Enhancement

Git hooks (via Husky, pre-commit, or shell scripts):

  • pre-commit: lint, format check, secret scan
  • commit-msg: conventional commit format enforcement

IDE config:

  • .editorconfig: tab size, line endings, charset
  • .vscode/settings.json: formatter, ruler, file exclusions
  • .vscode/extensions.json: recommended extensions

Read the full file on GitHub · 125 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. 4d ago First seen · 125 lines · 68 tokens per session scan A 1300d0978662

Subscribe to this mod's changes

dx-optimizer is an agent published in the GitHub repository kumaran-is/claude-code-onboarding (35 stars, last pushed 2mo ago), licensed MIT. It adds 68 tokens to every session and 1,075 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 2026-08-30.