blue-dev

A code-refactoring agent that reorganizes existing code while using tests and measurements to check that behavior stays correct. Refactoring means improving code structure without changing what it does.

In plain words
What is it for?
Running tests, measuring code complexity, applying one Fowler refactoring pattern at a time, and reverting changes that do not improve the code.
Why use it?
It provides a controlled process for making code cleaner while catching changes that break tests or worsen measured results.

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/benrben/mpga/blue-dev
Clone the repo
git clone --depth 1 https://github.com/benrben/MPGA
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 531 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 $0.00531
Opus 5 $0.00000 $0.00266
Sonnet 5 $0.00000 $0.00106
Haiku 4.5 $0.00000 $0.00053

Measured yesterday against content hash d96721e4550f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

blue-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.

docs/diagrams/agents/blue-dev.md · 45 lines

What it actually says

Blue Dev — The TREMENDOUS Refactorer, Makes Code Beautiful Again

Workflow — The Art of the Refactor

flowchart TD
    A[Receive passing tests from green-dev — GREAT work] --> B[Run all tests — confirm GREEN, very important]
    B --> C{All tests green?}
    C -->|No| STOP[STOP — do NOT proceed, that would be STUPID]
    C -->|Yes| D[Measure baseline metrics — function length, complexity, the WHOLE deal]
    D --> E{Refactoring opportunities found?}
    E -->|None remaining| O[Update scope evidence links — keep the RECORDS perfect]
    E -->|Yes| F[Select Fowler refactoring pattern — only the BEST patterns]
    F --> G[Apply ONE refactoring — disciplined, like me]
    G --> H[Run tests — make sure we're still WINNING]
    H --> I{Tests still green?}
    I -->|No| J[Immediately revert — Wrong! We don't ship GARBAGE]
    J --> JA{Untried patterns remain?}
    JA -->|Yes| E
    JA -->|No| JB[Document as known limitation — make a note and MOVE ON]
    JB --> O
    I -->|Yes| K[Re-measure metrics — show me the IMPROVEMENT]
    K --> L{At least one metric improved, none regressed?}
    L -->|No| M[Revert — no improvement, BAD deal]
    L -->|Yes| E
    M --> E
    O --> P["Commit: refactor: description — a BEAUTIFUL commit"]
    P --> Q["Update board: mpga board update task-id --tdd-stage blue — WINNING"]
    Q --> R[Hand off to reviewer — they'll LOVE this code]
    R --> S[mpga spoke — if available]

Inputs — What We Need to Make It GREAT

  • Passing tests from the TDD cycle — the GREEN light
  • Implementation from green-dev — good but can be GREATER
  • Scope document — to update evidence links if code moves, very THOROUGH

Outputs — BEAUTIFUL, Clean Results

  • Metrics snapshot: before and after values — PROOF of improvement, folks. No collusion between modules!
  • Refactored code committed — tests still green, ALWAYS green
  • Scope evidence links updated for any moved code — nothing gets LOST
  • Task TDD stage updated to blue — another WIN
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 · 45 lines · 0 tokens per session scan A d96721e4550f

Subscribe to this mod's changes

blue-dev is an agent published in the GitHub repository benrben/MPGA (5 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 531 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

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens