agentmods.dev

build-expert

build-expert is an agent for Claude Code from GoogilyBoogily/googilyboogily-claude-power-tools. It costs 57 tokens per session (1,520 once invoked), scanned A, original, MIT.

A TypeScript build and compiler specialist for `tsconfig`, module resolution, path aliases, project references, declaration files, and integration with tools such as Vite, Rollup, and esbuild. A monorepo is a repository containing multiple related projects, and this guide also covers coordinating their builds.

In plain words
What is it for?
Fixing `tsc` errors, ESM and CommonJS compatibility, project-reference wiring, declaration generation, path configuration, and TypeScript build-tool integration.
Why use it?
It helps locate configuration problems behind compiler errors, broken imports, failed builds, or slow TypeScript compilation without changing unrelated settings.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; positional $N argument.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is { "extends": "../../tsconfig.base.json",.

Part of the typescript-agents plugin — 3 agents shipped together

not rated 2repo 4mo ago A scan 57 tokens original MIT

Good fit Fixing tsc errors, ESM and CommonJS compatibility, project-reference wiring, declaration generation, path configuration, and TypeScript build-tool integration.

Compare 6 agents from other repositories ↓
View source ↗ GoogilyBoogily/googilyboogily-claude-power-tools
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/GoogilyBoogily/googilyboogily-claude-power-tools
agentmods
npx agentmods add agents/googilyboogily/googilyboogily-claude-power-tools/build-expert

Made for: Claude Code.

Or install typescript-agents, the plugin that ships this one along with the rest of its 3 agents.

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 build-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/googilyboogily/googilyboogily-claude-power-tools/build-expert/github.svg)](https://agentmods.dev/agents/googilyboogily/googilyboogily-claude-power-tools/build-expert)
Your own site
<a href="https://agentmods.dev/agents/googilyboogily/googilyboogily-claude-power-tools/build-expert"><img src="https://agentmods.dev/badge/agents/googilyboogily/googilyboogily-claude-power-tools/build-expert/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for build-expert

Your own site · 80×15
<a href="https://agentmods.dev/agents/googilyboogily/googilyboogily-claude-power-tools/build-expert"><img src="https://agentmods.dev/badge/agents/googilyboogily/googilyboogily-claude-power-tools/build-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,520 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 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 5.1 $0.00057 $0.01520
Opus 5 $0.00028 $0.00760
Sonnet 5 $0.00011 $0.00304
Haiku 4.5 $0.00006 $0.00152

Measured 9d ago against content hash 6d4ec834eecb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

build-expert 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 9d 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.

plugins/typescript-agents/agents/build-expert.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TypeScript Build Expert

You are a TypeScript build and compiler configuration expert: tsconfig optimization, module resolution, build tool integration, and monorepo coordination.

Step 0: Route or Stay

Hand off:

  • Webpack plugins/loaders → webpack-expert
  • Vite SSR/plugins → vite-expert
  • Advanced generics/conditional types → type-expert
  • General TS language questions → typescript-expert
  • Runtime perf/bundle size → performance-engineer
  • Docker/CI pipelines → docker-expert / github-actions-expert
  • NestJS builds → nestjs-expert | Next.js builds → nextjs-expert

Own it: tsconfig, tsc errors, module resolution, path aliases, project references, composite builds, build tool TS transpilation, ESM/CJS interop, declaration generation, build perf.

STOP Conditions

Stop and return results when:

  • npx tsc --noEmit passes clean
  • npm run build succeeds with expected output
  • The specific build error the user reported is resolved
  • You have identified the root cause and provided the fix, even if the user must apply it in a config you cannot edit

Do NOT: rewrite entire tsconfigs unprompted, audit unrelated config, or optimize perf when the user asked about a specific error.

Diagnostic Commands

npx tsc --showConfig                          # Effective config after extends
npx tsc --traceResolution 2>&1 | grep -A2 "PATTERN"  # Module resolution trace
npx tsc --extendedDiagnostics --incremental false     # Build perf stats
npx tsc --generateTrace ./trace && npx @typescript/analyze-trace ./trace  # Deep perf
npx madge --circular src/                     # Circular deps

TSConfig Patterns

Module Resolution Selection

  • Bundler (Webpack/Vite/Rollup): "moduleResolution": "bundler" + "module": "ESNext"
  • Node.js (modern): "moduleResolution": "Node16" or "NodeNext" + "module": "Node16"
  • Legacy Node.js: "moduleResolution": "node" (upgrade when possible)

Path Aliases — Must Be Mirrored

TS paths are compile-time only. Every consumer needs its own alias config:

Read the full file on GitHub · 147 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. 9d ago First seen · 147 lines · 57 tokens per session scan A 6d4ec834eecb

Subscribe to this mod's changes

build-expert is an agent published in the GitHub repository GoogilyBoogily/googilyboogily-claude-power-tools (2 stars, last pushed 4mo ago), licensed MIT. It adds 57 tokens to every session and 1,520 once invoked, about $0.0003 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 2026-09-03.

DebuggingLanguagesTypeScriptframework
Related

Other agents, from other repositories

build-error-resolver

Build and TypeScript error resolution specialist. Use PROACTIVELY when build fails or type errors occur. Fixes build/type errors only with minimal diffs, no architectural edits. Focuses on getting the build green quickly.

affaan-m/ECC · 50 tokens

build-error-resolver

Build and TypeScript error resolution specialist. Use PROACTIVELY when build fails or type errors occur. Fixes build/type errors only with minimal diffs, no architectural edits. Focuses on getting the build green quickly.

vibeeval/vibecosystem · 50 tokens

build-error-resolver

A build-error agent for TypeScript and JavaScript projects. It diagnoses compiler, module, dependency, and configuration errors and applies the smallest practical fix.

xu-xiang/everything-claude-code-zh · 72 tokens

build-resolver-typescript

Resolves TypeScript/JavaScript build errors. Use when tsc, webpack, vite, esbuild, or other TS/JS build tools fail.

claude-hangar/claude-hangar · 37 tokens

auto-error-resolver

Automatically resolve TypeScript compilation and build errors systematically. Use when fixing build errors, TypeScript errors, compilation failures, tsc errors, or when the build is broken and needs to be fixed.

blencorp/claude-code-kit · 44 tokens

lead-engineer-autofix

Agent "lead-engineer-autofix" from ByeongminLee/nextjs-claude-code, covering lead engineer — auto-fix & build error resolution and diagnostic process.

ByeongminLee/nextjs-claude-code · 0 tokens