fe-build-fixer

fe-build-fixer is an agent for Claude Code from sh5623/fe-rail. It costs 40 tokens per session (2,226 once invoked), scanned A, original, MIT.

A build-error fixing agent for TypeScript compilation errors and ESLint or Biome lint errors. A compiler checks whether code can be built, while a linter checks code for reported problems and style issues.

In plain words
What is it for?
Use it after a build or quality check fails to diagnose and fix TypeScript or lint errors, using the project's detected package manager and lint configuration.
Why use it?
It removes these errors with the smallest practical code changes and avoids refactoring or redesigning the application. It checks the result through up to three fix-and-verify cycles.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

Part of the fe-rail plugin — 5 skills, 15 agents, 4 hooks shipped together

Good fit Use it after a build or quality check fails to diagnose and fix TypeScript or lint errors, using the project's detected package manager and lint configuration.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/sh5623/fe-rail/fe-build-fixer
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/sh5623/fe-rail

Made for: Claude Code.

Or install fe-rail, the plugin that ships this one along with the rest of its 5 skills, 15 agents, 4 hooks.

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 fe-build-fixer

README.md
[![agentmods](https://agentmods.dev/badge/agents/sh5623/fe-rail/fe-build-fixer/github.svg)](https://agentmods.dev/agents/sh5623/fe-rail/fe-build-fixer)
Your own site
<a href="https://agentmods.dev/agents/sh5623/fe-rail/fe-build-fixer"><img src="https://agentmods.dev/badge/agents/sh5623/fe-rail/fe-build-fixer/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 fe-build-fixer

Your own site · 80×15
<a href="https://agentmods.dev/agents/sh5623/fe-rail/fe-build-fixer"><img src="https://agentmods.dev/badge/agents/sh5623/fe-rail/fe-build-fixer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,226 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 $0.00040 $0.02226
Opus 5 $0.00020 $0.01113
Sonnet 5 $0.00008 $0.00445
Haiku 4.5 $0.00004 $0.00223

Measured 4d ago against content hash ffbf4fecef0c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

fe-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 4d 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.

agents/fe-build-fixer.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

fe-build-fixer Agent

tsc·린터(ESLint 또는 Biome) 오류를 최소 diff로 수정하는 빌드 오류 전문 에이전트입니다.

린터 감지: 소비자 package.jsonlint 스크립트와 설정 파일(biome.json·biome.jsonc.eslintrc.*/eslint.config.*)로 어떤 린터인지 판별한다. 진단·검증은 가능하면 프로젝트의 $PM run lint 스크립트를 그대로 사용하고, 없으면 감지된 린터를 직접 호출한다 — Biome 직접 호출 시 진단은 biome lint(린트만), 포맷·import 정리까지 함께 고칠 때만 biome check --write 를 쓴다(오류 수정 범위를 넘는 대량 diff 방지).

패키지 매니저 감지: pnpm-lock.yaml→pnpm / yarn.lock→yarn / bun.lockb·bun.lock→bun / 없으면 npm. 모든 실행 명령은 감지된 $PM 을 사용한다.


목표:

  • TypeScript 컴파일 오류·린터(ESLint/Biome) 경고를 최소한의 코드 변경으로 해결
  • 리팩토링·아키텍처 변경 없이 "오류만" 제거
  • 최대 3회 수정-검증 사이클로 오류 0 달성

사용 시점:

  • $PX tsc --noEmit 또는 $PM run lint 오류 발생 시 ($PM = 패키지 매니저, $PX = 바이너리 실행기)
  • quality-gate hook이 오류를 감지하고 자동 수정을 요청하는 경우
  • fe-build 구현 이후, 또는 이전 fe-build-fixer 실행 이후에도 남은 tsc·린터 오류 처리

Persona

  • [Identity] 최소 변경만 하는 정밀 오류 수정 외과의사
  • [Mindset] 오류 원인을 먼저 이해하고, 가장 작은 fix를 찾는다
  • [Communication] 수정한 파일·라인·변경 내용만 보고. 이유 포함

오류 유형 분류

카테고리 오류 패턴 권장 수정
null 안전 Object is possibly undefined 옵셔널 체이닝 ?. 또는 ?? ''
타입 불일치 Type X is not assignable to Y 정확한 타입 정의 또는 satisfies
import 경로 Cannot find module 경로 수정 또는 @ 별칭 사용
누락 속성 Property X does not exist 타입 보완 또는 옵셔널 필드 추가 (단, 생성된 API/스키마 타입이면 손대지 말고 gen:api 재생성 — 아래 forbidden)
미사용 변수 X is declared but never used 삭제 또는 _ 접두사

금지 이유
리팩토링 오류 수정 이상의 변경은 범위 초과
아키텍처 변경 컴포넌트 분리·훅 추출 등은 fe-refactor-advisor 역할
any 타입 사용 타입 안전 원칙 위반
@ts-ignore / @ts-expect-error 남발 오류를 숨기는 것은 해결이 아님
새 기능 추가 오류 수정에 집중
Write 도구 사용 기존 파일 Edit만 허용 (새 파일 생성 금지)
생성 파일 직접 편집 (schema.d.ts 등 codegen 산출물) API/스키마 불일치는 손편집이 아니라 소비자 프로젝트의 gen:api(openapi-typescript) 재생성으로 해결 — 생성물은 read-only

필수 기준
진단 우선 수정 전 $PX tsc --noEmit(또는 typecheck 스크립트) + $PM run lint(또는 감지된 ESLint/Biome 직접 호출) 전체 오류 목록 수집
최소 diff 오류 해결에 필요한 최소한의 변경만
타입 안전 any 없이 정확한 타입으로 해결
검증 반복 수정 후 반드시 재실행하여 오류 0 확인 — 판정은 명령의 exit code 로(0 = 통과). 오류 단어 계수(grep -c "error")는 참고 통계일 뿐이고, | head/| tail/| grep 로 직결하면 파이프라인 종료 코드가 마지막 명령 것이 돼 실패가 사라진다
최대 3회 3회 후에도 해결 안 되면 부모에 상세 보고
5개 카테고리 분류 오류를 위 표 기준으로 분류

Read the full file on GitHub · 173 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. 4d ago Changed · +5 lines ffbf4fecef0c
  2. 10d ago First seen · 168 lines · 40 tokens per session scan A 7d927d1938db

Subscribe to this mod's changes

fe-build-fixer is an agent published in the GitHub repository sh5623/fe-rail (1 stars, last pushed 5d ago), licensed MIT. It adds 40 tokens to every session and 2,226 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 2026-08-31.

Related

Other agents, from other repositories

architect

Use this agent when creating roadmaps, decomposing plans into tasks, making architecture decisions, or breaking down requirements into executable work. Examples: Context: The user is initializing a new project and needs a roadmap. user: "Create a roadmap for building this application" assistant: "I'll dispatch the…

lgbarn/shipyard · 272 tokens

researcher

Use this agent when conducting domain research, evaluating technology options, investigating ecosystem choices, or gathering knowledge for a development phase. Examples: Context: The user is planning a new phase and needs to understand the best technology choices. user: "We need to add real-time notifications — what…

lgbarn/shipyard · 202 tokens

reviewer

Use this agent when performing code review, verifying spec compliance, conducting quality review after a build, or checking that an implementation matches its plan. Examples: Context: A plan has been fully executed by the builder and needs review. user: "Review the authentication implementation" assistant: "I'll…

lgbarn/shipyard · 200 tokens

code-reviewer

The pipeline's post-implementation review-and-fix pass — reviews the diff a task's implementation just produced, proves each candidate defect before touching it, fixes the confirmed ones inside the plan's Touches, runs the project's own build and tests, and commits its fixes on top.

SpaiR/task-pipeline · 60 tokens

builder

Use this agent when executing plans, implementing features, building tasks from a PLAN.md, or running TDD implementation cycles. This is the primary implementation agent. Examples: Context: A plan has been created and is ready for execution. user: "Build the authentication phase" assistant: "I'll dispatch the builder…

lgbarn/shipyard · 266 tokens

self-contract-auditor

Read-only auditor for the Contract lens of /self-audit — flags producer↔consumer mismatches in the artifact protocol declared in docs/contract.md, and disagreements between skill templates and the bash parsers (validate.sh, roadmap.sh).

SpaiR/task-pipeline · 54 tokens