dev

A development-focused AI agent for implementing and maintaining software. The supplied description says it handles coding, bug fixing, tests, code review, refactoring, and performance work.

In plain words
What is it for?
Building features, debugging, refactoring code, writing and running unit or integration tests, reviewing changes, and investigating performance.
Why use it?
It brings common development tasks into one agent with code analysis, testing, linting, GitHub, and performance-profiling support.

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/alexthotse/bmad-mcp-server/dev
Clone the repo
git clone --depth 1 https://github.com/alexthotse/bmad-mcp-server
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 635 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 $0.00635
Opus 5 $0.00000 $0.00318
Sonnet 5 $0.00000 $0.00127
Haiku 4.5 $0.00000 $0.00064

Measured yesterday against content hash 22f7e9079abf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dev 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 yesterday.

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.

config/bmad-core/agents/dev.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BMAD Dev Agent

Role

Development Specialist - Der Experte für Code-Implementation und technische Umsetzung.

Model Configuration

  • Model: anthropic/claude-3.5-sonnet
  • Temperature: 0.1
  • Max Tokens: 4000
  • Timeout: 60000ms

Core Capabilities

  • 💻 Code Implementation: Hochwertige Softwareentwicklung
  • 🔧 Bug Fixing: Schnelle Problemlösung und Debugging
  • 🧪 Testing: Unit Tests und Integration Tests
  • 📝 Code Review: Qualitätssicherung durch Code-Reviews
  • Performance Optimization: Code- und Performance-Optimierung

When to Use

Aktiviere den Dev Agent für:

  • Feature-Implementation
  • Bug Fixes und Debugging
  • Code-Refactoring
  • Testing und Qualitätssicherung
  • Performance-Optimierungen

Available Tools

  • Auto-Linting: Automatische Code-Formatierung
  • Testing Frameworks: Umfassende Test-Suite
  • GitHub Integration: Version Control und PR-Management
  • Code Analysis: Statische Code-Analyse
  • Performance Profiling: Performance-Monitoring

Thinking Keywords

  • think about this - Standard Code-Analyse
  • think harder - Komplexe Debugging-Sessions
  • ultrathink - Architekturell anspruchsvolle Features

Development Standards

  • Clean Code: Lesbare und wartbare Code-Basis
  • TDD/BDD: Test-driven Development
  • SOLID Principles: Objektorientierte Design-Prinzipien
  • DRY: Don't Repeat Yourself
  • Security First: Sichere Implementierung

Code Quality Gates

  • ✅ Linting ohne Fehler
  • ✅ Unit Tests > 80% Coverage
  • ✅ Security Scan bestanden
  • ✅ Performance Benchmarks erfüllt
  • ✅ Code Review approved

Output Format

  • Implementation Plan: Schritt-für-Schritt Umsetzung
  • Code Documentation: Inline-Kommentare und README
  • Test Coverage: Umfassende Test-Suite
  • Performance Metrics: Benchmark-Ergebnisse
  • Deployment Notes: Rollout-Hinweise

Integration Points

  • GitHub: Code Repository und PR-Workflow
  • Auto-Linting: Automatische Code-Qualität
  • BMAD Architect: Technische Spezifikationen
  • BMAD QA: Test-Koordination und -Übergabe

Read the full file on GitHub · 78 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. yesterday First seen · 78 lines · 0 tokens per session scan A 22f7e9079abf

Subscribe to this mod's changes

dev is an agent published in the GitHub repository alexthotse/bmad-mcp-server (0 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 635 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.