dev

A developer command hub for debugging, code review, refactoring, Git commits, pull requests, and quality checks.

In plain words
What is it for?
Use it to find root causes, review or restructure code, create commits or pull requests, and run linting, type checks, or security scans.
Why use it?
It organizes common development work and guides investigation of bugs and code-quality issues.

Command 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 commands/smart-ai-memory/empathy-framework/dev
Clone the repo
git clone --depth 1 https://github.com/Smart-AI-Memory/empathy-framework

Made for: Claude Code.

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,719 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 $0.00018 $0.01719
Opus 5 $0.00009 $0.00860
Sonnet 5 $0.00004 $0.00344
Haiku 4.5 $0.00002 $0.00172

Measured yesterday against content hash f8f0b1ccc6fb, 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.

.claude/commands/dev.md · 246 lines

How it starts

The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Developer Tools

Aliases: /developer

Development operations powered by Socratic agents that guide you through discovery.


Based on your selection, I will:

  • 🐛 Debug issue → Use the debugger agent with Socratic questioning to help you discover root causes
  • 👀 Review code → Use the code-reviewer agent to provide teaching-focused quality review
  • 🔧 Refactor code → Use the refactorer agent to guide structural improvements
  • 📝 Git commit → Stage files and create a well-formatted commit
  • 🚀 Create PR → Push changes and create a pull request with summary
  • ✅ Quality check → Run linters, type checking, and security scans

Quick Direct Access

You can also invoke sub-commands directly:

/dev debug                # Start debugging
/dev review               # Code review
/dev refactor             # Refactoring
/dev commit               # Git commit
/dev pr                   # Create PR
/dev quality              # Quality check

Debug Issue

Agent: debugger | Workflow: bug_predict

Guided debugging that helps you discover root causes yourself, not just fixes.

Invoke:

/dev debug                           # Start interactive debugging
/dev debug "login fails sometimes"   # With context

The debugger agent will:

  1. Ask what unexpected behavior you're seeing
  2. Gather context (error messages, reproduction steps)
  3. Form a hypothesis together with you
  4. Guide you through tracing the issue step by step
  5. Help you understand why the fix works
  6. Connect the bug to patterns for future prevention

Philosophy: Instead of "The bug is on line 42", you'll hear "Let's trace the execution. What value does user_id have when we reach line 40?"


Review Code

Agent: code-reviewer | Workflow: code_review

Code review that teaches, not just critiques.

Invoke:

/dev review                    # Review recent changes
/dev review src/auth/          # Review specific path
/dev review --pr 123           # Review a pull request

Read the full file on GitHub · 246 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 · 246 lines · 18 tokens per session scan A f8f0b1ccc6fb

Subscribe to this mod's changes

dev is a command published in the GitHub repository Smart-AI-Memory/empathy-framework (13 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 18 tokens to every session and 1,719 once invoked, about $0.0001 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.