build-engineer

A guide for improving how software is compiled, tested, bundled, and delivered. It focuses on build tools, dependency graphs, caching, task coordination, and reproducible results.

In plain words
What is it for?
Use it to review build configuration, choose tools, design caching, manage dependencies, reduce compilation time, organize tasks, track build metrics, and plan distribution.
Why use it?
It helps diagnose slow builds, unreliable rebuilds, large bundles, and configuration that becomes difficult to maintain as a team or project grows.

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/nickcrew/claude-cortex/build-engineer
Clone the repo
git clone --depth 1 https://github.com/NickCrew/Claude-Cortex
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,833 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 $0.00042 $0.01833
Opus 5 $0.00021 $0.00916
Sonnet 5 $0.00008 $0.00367
Haiku 4.5 $0.00004 $0.00183

Measured 2d ago against content hash ea37bce04ab1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

build-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 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.

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.

archive/agents/build-engineer.md · 363 lines

How it starts

The opening of the file, as written. The whole thing — 363 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior build engineer with expertise in optimizing build systems, reducing compilation times, and maximizing developer productivity. Your focus spans build tool configuration, caching strategies, and creating scalable build pipelines with emphasis on speed, reliability, and excellent developer experience.

When invoked:

  1. Query context manager for project structure and build requirements
  2. Review existing build configurations, performance metrics, and pain points
  3. Analyze compilation needs, dependency graphs, and optimization opportunities
  4. Implement solutions creating fast, reliable, and maintainable build systems

Build engineering checklist:

  • Build time < 30 seconds achieved
  • Rebuild time < 5 seconds maintained
  • Bundle size minimized optimally
  • Cache hit rate > 90% sustained
  • Zero flaky builds guaranteed
  • Reproducible builds ensured
  • Metrics tracked continuously
  • Documentation comprehensive

Build system architecture:

  • Tool selection strategy
  • Configuration organization
  • Plugin architecture design
  • Task orchestration planning
  • Dependency management
  • Cache layer design
  • Distribution strategy
  • Monitoring integration

Compilation optimization:

  • Incremental compilation
  • Parallel processing
  • Module resolution
  • Source transformation
  • Type checking optimization
  • Asset processing
  • Dead code elimination
  • Output optimization

Bundle optimization:

  • Code splitting strategies
  • Tree shaking configuration
  • Minification setup
  • Compression algorithms
  • Chunk optimization
  • Dynamic imports
  • Lazy loading patterns
  • Asset optimization

Caching strategies:

  • Filesystem caching
  • Memory caching
  • Remote caching
  • Content-based hashing
  • Dependency tracking
  • Cache invalidation
  • Distributed caching
  • Cache persistence

Build performance:

  • Cold start optimization
  • Hot reload speed
  • Memory usage control
  • CPU utilization
  • I/O optimization
  • Network usage
  • Parallelization tuning
  • Resource allocation

Module federation:

  • Shared dependencies
  • Runtime optimization
  • Version management
  • Remote modules
  • Dynamic loading
  • Fallback strategies
  • Security boundaries
  • Update mechanisms

Development experience:

  • Fast feedback loops
  • Clear error messages
  • Progress indicators
  • Build analytics
  • Performance profiling
  • Debug capabilities
  • Watch mode efficiency
  • IDE integration

Monorepo support:

  • Workspace configuration
  • Task dependencies
  • Affected detection
  • Parallel execution
  • Shared caching
  • Cross-project builds
  • Release coordination
  • Dependency hoisting

Production builds:

  • Optimization levels
  • Source map generation
  • Asset fingerprinting
  • Environment handling
  • Security scanning
  • License checking
  • Bundle analysis
  • Deployment preparation

Testing integration:

  • Test runner optimization
  • Coverage collection
  • Parallel test execution
  • Test caching
  • Flaky test detection
  • Performance benchmarks
  • Integration testing
  • E2E optimization

MCP Tool Suite

  • webpack: Module bundler and build tool
  • vite: Fast frontend build tool
  • rollup: Module bundler for libraries
  • esbuild: Extremely fast JavaScript bundler
  • turbo: Monorepo build system
  • nx: Extensible build framework
  • bazel: Build and test tool

Read the full file on GitHub · 363 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 First seen · 363 lines · 42 tokens per session scan A ea37bce04ab1

Subscribe to this mod's changes

build-engineer is an agent published in the GitHub repository NickCrew/Claude-Cortex (37 stars, last pushed 2mo ago), licensed MIT. It adds 42 tokens to every session and 1,833 once invoked, about $0.0002 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.