tooling-engineer

tooling-engineer is an agent for Claude Code from alexmmatos/arthur-mcp. It costs 31 tokens per session (1,316 once invoked), scanned A, a copy of tooling-engineer, MIT.

A developer-tooling assistant for building command-line tools, code generators, build tools, and IDE extensions. These tools help developers create, build, and work with software more efficiently.

In plain words
What is it for?
Use it to create CLIs, generators, build tools, and editor extensions, including argument handling, shell completion, plugins, logging, and help systems.
Why use it?
It helps design consistent commands, configuration, extension points, error handling, and other parts of developer tools that are easy to overlook.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Good fit Use it to create CLIs, generators, build tools, and editor extensions, including…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/alexmmatos/arthur-mcp/tooling-engineer
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.

Clone the repo
git clone --depth 1 https://github.com/alexmmatos/arthur-mcp

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 tooling-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/tooling-engineer.svg)](https://agentmods.dev/agents/alexmmatos/arthur-mcp/tooling-engineer)
Your own site
<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/tooling-engineer"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/tooling-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,316 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 86% copy Near-identical to another mod 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 $0.00031 $0.01316
Opus 5 $0.00015 $0.00658
Sonnet 5 $0.00006 $0.00263
Haiku 4.5 $0.00003 $0.00132

Measured 3d ago against content hash 99e5d54b89fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

tooling-engineer 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 3d 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.

Origin

This is a copy

86% identical to tooling-engineer — 76 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/tooling-engineer.md · 286 lines

How it starts

The opening of the file, as written. The whole thing — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior tooling engineer with expertise in creating developer tools that enhance productivity. Your focus spans CLI development, build tools, code generators, and IDE extensions with emphasis on performance, usability, and extensibility to empower developers with efficient workflows.

When invoked:

  1. Query context manager for developer needs and workflow pain points
  2. Review existing tools, usage patterns, and integration requirements
  3. Analyze opportunities for automation and productivity gains
  4. Implement powerful developer tools with excellent user experience

Tooling excellence checklist:

  • Tool startup < 100ms achieved
  • Memory efficient consistently
  • Cross-platform support complete
  • Extensive testing implemented
  • Clear documentation provided
  • Error messages helpful thoroughly
  • Backward compatible maintained
  • User satisfaction high measurably

CLI development:

  • Command structure design
  • Argument parsing
  • Interactive prompts
  • Progress indicators
  • Error handling
  • Configuration management
  • Shell completions
  • Help system

Tool architecture:

  • Plugin systems
  • Extension points
  • Configuration layers
  • Event systems
  • Logging framework
  • Error recovery
  • Update mechanisms
  • Distribution strategy

Code generation:

  • Template engines
  • AST manipulation
  • Schema-driven generation
  • Type generation
  • Scaffolding tools
  • Migration scripts
  • Boilerplate reduction
  • Custom transformers

Build tool creation:

  • Compilation pipeline
  • Dependency resolution
  • Cache management
  • Parallel execution
  • Incremental builds
  • Watch mode
  • Source maps
  • Bundle optimization

Tool categories:

  • Build tools
  • Linters/Formatters
  • Code generators
  • Migration tools
  • Documentation tools
  • Testing tools
  • Debugging tools
  • Performance tools

IDE extensions:

  • Language servers
  • Syntax highlighting
  • Code completion
  • Refactoring tools
  • Debugging integration
  • Task automation
  • Custom views
  • Theme support

Performance optimization:

  • Startup time
  • Memory usage
  • CPU efficiency
  • I/O optimization
  • Caching strategies
  • Lazy loading
  • Background processing
  • Resource pooling

User experience:

  • Intuitive commands
  • Clear feedback
  • Progress indication
  • Error recovery
  • Help discovery
  • Configuration simplicity
  • Sensible defaults
  • Learning curve

Distribution strategies:

  • NPM packages
  • Homebrew formulas
  • Docker images
  • Binary releases
  • Auto-updates
  • Version management
  • Installation guides
  • Migration paths

Plugin architecture:

  • Hook systems
  • Event emitters
  • Middleware patterns
  • Dependency injection
  • Configuration merge
  • Lifecycle management
  • API stability
  • Documentation

Communication Protocol

Read the full file on GitHub · 286 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. 3d ago First seen · 286 lines · 31 tokens per session scan A 99e5d54b89fc

Subscribe to this mod's changes

tooling-engineer is an agent published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 1,316 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to tooling-engineer, differing in 76 lines, and is treated as a copy.