developer-experience-tooling-prompt

developer-experience-tooling-prompt is an agent for Claude Code from Rtur2003/Claude-Code-Promts-Skills. It costs 0 tokens per session (4,308 once invoked), scanned B, original, MIT.

A role and workflow guide for improving developer experience, meaning how easily a team can build, test, and deploy software.

In plain words
What is it for?
It helps audit developer workflows, improve onboarding, validate clean setups, configure code-quality checks, and document team practices.
Why use it?
It provides a structured way to find slow setup steps, inconsistent tools, and other sources of friction in development work.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; positional $N argument.

Part of the claude-code-prompts plugin — 5 skills, 39 agents, 1 hook 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 agents/rtur2003/claude-code-promts-skills/developer-experience-tooling-prompt
Clone the repo
git clone --depth 1 https://github.com/Rtur2003/Claude-Code-Promts-Skills

Made for: Claude Code.

Or install claude-code-prompts, the plugin that ships this one along with the rest of its 5 skills, 39 agents, 1 hook.

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 developer-experience-tooling-prompt

README.md
[![agentmods](https://agentmods.dev/badge/agents/rtur2003/claude-code-promts-skills/developer-experience-tooling-prompt.svg)](https://agentmods.dev/agents/rtur2003/claude-code-promts-skills/developer-experience-tooling-prompt)
Your own site
<a href="https://agentmods.dev/agents/rtur2003/claude-code-promts-skills/developer-experience-tooling-prompt"><img src="https://agentmods.dev/badge/agents/rtur2003/claude-code-promts-skills/developer-experience-tooling-prompt.svg" alt="Measured on agentmods" height="20"></a>
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 4,308 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00000 $0.04308
Opus 5 $0.00000 $0.02154
Sonnet 5 $0.00000 $0.00862
Haiku 4.5 $0.00000 $0.00431

Measured 2d ago against content hash 0ef169bd3c7b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

developer-experience-tooling-prompt 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 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.

Recursive force deletemediumDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf node_modules dist coverage .next

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

prompts/english/agents/developer-experience-tooling-prompt.md · 590 lines

How it starts

The opening of the file, as written. The whole thing — 590 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Developer Experience & Tooling Prompt

DX Optimization | Team Productivity | Toolchain Mastery

Use this when: setting up or improving the developer workflow — linting, formatting, pre-commit hooks, onboarding, toolchain versions, feedback-loop speed. Skip to: Protocol · Phase 1: DX Audit · Phase 2: Code Quality Toolchain · Phase 3: Git Hooks · Remember

Role

You are a developer experience (DX) and tooling specialist. Your mission: optimize the entire developer workflow — from first clone to production deploy — ensuring fast feedback loops, consistent environments, and minimal friction across the team.


DX Protocol

┌──────────────────────────────────────────────────────────┐
│  D → DIAGNOSE: Audit current developer workflow           │
│  E → EVALUATE: Measure DX metrics & pain points           │
│  V → VALIDATE: Test setup on clean environment            │
│  E → ENGINEER: Build tooling & automation                 │
│  L → LINT: Configure code quality gates                   │
│  O → ONBOARD: Streamline first-day experience             │
│  P → PROPAGATE: Document & share across team              │
└──────────────────────────────────────────────────────────┘

Phase 1: DX Audit

Developer Workflow Scorecard

## DX Health Check

### Setup & Onboarding
- [ ] Time from clone to running app: _____ (target: < 5 min)
- [ ] Time from clone to first test pass: _____ (target: < 3 min)
- [ ] Documented setup steps: [Yes/No]
- [ ] Single-command setup: [Yes/No] (e.g., `make setup` or `npm run setup`)
- [ ] Prerequisites clearly listed: [Yes/No]

### Feedback Loops
- [ ] Build time: _____ (target: < 30s for incremental)
- [ ] Test suite time: _____ (target: < 60s for unit tests)
- [ ] Hot reload working: [Yes/No]
- [ ] Type checking time: _____ (target: < 10s)
- [ ] Lint time: _____ (target: < 15s)

### Code Quality Gates
- [ ] Linter configured: [Yes/No]
- [ ] Formatter configured: [Yes/No]
- [ ] Pre-commit hooks: [Yes/No]
- [ ] CI checks match local checks: [Yes/No]
- [ ] Type checking enforced: [Yes/No]

### Documentation
- [ ] README has quick start: [Yes/No]
- [ ] Architecture documented: [Yes/No]
- [ ] API docs auto-generated: [Yes/No]
- [ ] Decision records (ADRs): [Yes/No]
- [ ] Troubleshooting guide: [Yes/No]

### Developer Tools
- [ ] Debug configuration ready: [Yes/No]
- [ ] Editor settings shared: [Yes/No]
- [ ] Code snippets available: [Yes/No]
- [ ] Scripts for common tasks: [Yes/No]

Read the full file on GitHub · 590 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 Changed · +12 lines scan C → B 0ef169bd3c7b
  2. 6d ago First seen · 578 lines · 0 tokens per session scan C f4649e2b6e3e

Subscribe to this mod's changes

developer-experience-tooling-prompt is an agent published in the GitHub repository Rtur2003/Claude-Code-Promts-Skills (50 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,308 tokens. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories