build-fix

build-fix is a skill for Claude Code from JeonJe/claude-plugins. It costs 49 tokens per session (611 once invoked), scanned A, original, MIT.

A step-by-step process for fixing build and type-checking errors in projects such as TypeScript, Java, Python, or Rust.

In plain words
What is it for?
Use it to repair local or continuous-integration build failures, type errors, or selected compiler error codes.
Why use it?
It isolates errors one at a time and rebuilds after each change, making it easier to see what was fixed and whether new errors appeared.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md.

Part of the dev-kit plugin — 6 skills shipped together

Good fit Use it to repair local or continuous-integration build failures, type errors, or…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jeonje/claude-plugins/build-fix
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.

Any agent
npx skills add JeonJe/claude-plugins --skill build-fix
Clone the repo
git clone --depth 1 https://github.com/JeonJe/claude-plugins

Made for: Claude Code.

Or install dev-kit, the plugin that ships this one along with the rest of its 6 skills.

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-fix

README.md
[![agentmods](https://agentmods.dev/badge/skills/jeonje/claude-plugins/build-fix.svg)](https://agentmods.dev/skills/jeonje/claude-plugins/build-fix)
Your own site
<a href="https://agentmods.dev/skills/jeonje/claude-plugins/build-fix"><img src="https://agentmods.dev/badge/skills/jeonje/claude-plugins/build-fix.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 611 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 $0.00049 $0.00611
Opus 5 $0.00024 $0.00305
Sonnet 5 $0.00010 $0.00122
Haiku 4.5 $0.00005 $0.00061

Measured 6d ago against content hash 7ad128ec34fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

build-fix 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 6d 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/dev-kit/skills/build-fix/SKILL.md · 70 lines

What it actually says

Build and Fix

Incrementally fix build/type errors — any stack (tsc, gradle/javac, mypy, cargo 등). 예시는 TS 기준.

Use Cases

1. 빌드 에러 수정

  • Input: "/build-fix"
  • Action: npm run build → 에러 파싱 → 파일별 그룹핑 → 순차 수정 → 재빌드 검증
  • Output: 수정 요약 (N개 해결, M개 잔존)

2. 특정 에러만 수정

  • Input: "/build-fix TS2322"
  • Action: 해당 에러 코드만 필터링 → 집중 수정
  • Output: 타겟 에러 해결 + 새 에러 여부 확인

3. CI 빌드 실패 복구

  • Input: "/build-fix" (CI 에러 로그 첨부)
  • Action: 에러 로그 분석 → 로컬 재현 → 수정 → 빌드 성공 확인
  • Output: CI 통과 가능한 상태로 복구

Workflow

  1. Run the project's build/type-check command (npm run build, ./gradlew compileJava, mypy, cargo check 등 — 프로젝트 CLAUDE.md 우선)

  2. Parse error output:

    • Group by file
    • Sort by severity
  3. For each error:

    • Show error context (5 lines before/after)
    • Explain the issue
    • Propose fix
    • Apply fix
    • Re-run build
    • Verify error resolved
  4. Stop if:

    • Fix introduces new errors

    • 재빌드 후 동일 에러 코드가 잔존하거나 3회 연속 같은 에러가 반복됨

    • User requests pause

  5. Show summary:

    • Errors fixed
    • Errors remaining
    • New errors introduced

원칙:

  • 한 번에 하나의 에러만 수정한다. 여러 파일을 동시에 손대면 어떤 변경이 어떤 에러를 해결했는지 추적이 어려워진다.
  • 에러와 무관한 코드는 손대지 않는다. 리팩토링은 별도 단계에서 수행.

Done When

  • 빌드가 성공하거나, 잔존 에러가 보고됨
  • 수정/잔존/신규 에러 수가 요약됨
  • 에러: 같은 에러 3회 반복 시 사용자에게 알림 후 중단

Composability

  • 빌드 성공 후 데드코드 정리는 별도 단계
  • 에러 수정 완료 후 커밋 전 리뷰: squidward-review 플러그인
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. 6d ago First seen · 70 lines · 49 tokens per session scan A 7ad128ec34fd

Subscribe to this mod's changes

build-fix is a skill published in the GitHub repository JeonJe/claude-plugins (3 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 611 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.