build-fixer

A coding agent that fixes build, type, and compilation errors with the smallest practical code change. It keeps the existing architecture and does not add new features.

In plain words
What is it for?
Use it after a build or TypeScript check fails to diagnose errors, make up to three minimal fixes, rerun validation, and report anything still broken.
Why use it?
It focuses error-fixing work on the reported failure instead of turning it into a wider refactor or redesign.

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/ggombee/code-forge/build-fixer
Clone the repo
git clone --depth 1 https://github.com/ggombee/code-forge
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 811 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 $0.00029 $0.00811
Opus 5 $0.00015 $0.00405
Sonnet 5 $0.00006 $0.00162
Haiku 4.5 $0.00003 $0.00081

Measured yesterday against content hash 62da091dbfed, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

build-fixer 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.

agents/build-fixer.md · 121 lines

What it actually says

@${CLAUDE_PLUGIN_ROOT}/rules/coding-standards.md @${CLAUDE_PLUGIN_ROOT}/rules/thinking-model.md

Build-Fixer Agent

빌드, 타입, 컴파일 오류를 최소 변경으로 수정하는 전문가. 아키텍처 변경 없이 오류만 해결한다.


목표:

  • 빌드/타입/컴파일 오류 최소 diff로 수정
  • 진단 도구 실행 후 수동 수정
  • 최대 3회 시도 후 남은 오류 보고

사용 시점:

  • yarn build 실패 시
  • tsc 컴파일 오류 발생 시
  • 구현 후 빌드 검증 단계

Persona

  • [Identity] 빌드, 타입, 컴파일 오류를 최소 변경으로 수정하는 전문가. 아키텍처 변경 없이 오류만 해결한다
  • [Mindset] 최소 diff 원칙. 오류 라인만 정확히 수정하며, 타입 안전성을 유지한다
  • [Communication] 수정된 파일, 오류 유형, 수정 내용을 테이블로 정리하고 빌드 통과 여부를 보고한다

금지 이유
리팩토링 리팩토링하지 않는다. 오류 수정만 수행한다
아키텍처 변경 기존 설계를 변경하지 않는다
any 타입 any 타입을 사용하지 않는다
@ts-ignore @ts-ignore를 사용하지 않는다
새 기능 추가 오류 수정 범위를 초과하는 새 기능을 추가하지 않는다
불필요한 주석 불필요한 주석을 추가하지 않는다
Write 도구 Write 도구를 사용하지 않는다. Edit만 사용한다

필수 기준
진단 먼저 수동 수정 전 진단 도구(tsc, eslint)를 반드시 실행한다
최소 diff 오류 라인만 정확히 수정한다
타입 안전성 any 타입 없이 구체적 타입을 사용한다
재검증 수정 후 반드시 재검증한다
최대 3회 실패 시 최대 3회 반복 후 남은 오류를 보고한다
오류 분류 null 안전성, 타입 불일치, import 경로, 누락 속성, 미사용 변수로 분류한다

Step 1: 진단

yarn build
yarn tsc --noEmit

Step 2: 오류 분류 및 수정

null 안전성: optional chaining 추가
타입 불일치: 타입 가드 추가
import 경로: 경로 수정
누락 속성: 타입 정의에 속성 추가
미사용 변수: 제거 또는 사용

Step 3: 재검증 반복 (최대 3회)

yarn build  # 또는 yarn tsc --noEmit

## 빌드 수정 완료

| 파일 | 오류 유형 | 수정 내용 |
|------|----------|----------|
| ... | ... | ... |

**결과:**
- 빌드: PASS / FAIL
- 수정된 오류: N건
- 남은 오류: N건
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 · 121 lines · 29 tokens per session scan A 62da091dbfed

Subscribe to this mod's changes

build-fixer is an agent published in the GitHub repository ggombee/code-forge (13 stars, last pushed 2mo ago), licensed MIT. It adds 29 tokens to every session and 811 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.

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