verification-engine
Use when verifying build/test/lint before commit, PR, or completion claims.
Skill by sangrokjung
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/sangrokjung-verification-engine
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: testing, data, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/verification-engine
What's inside
- Skill name
verification-engine- Description
- Use when verifying build/test/lint before commit, PR, or completion claims. Runs verification pipeline in fresh subagent context with auto-repair. Triggers on /handoff-verify, pre-commit check, build verification, test validation.
- License
- MIT
- Instructions
- 255 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
## 검증 원칙
Iron Law, Gate Function, Common Failures 체크리스트는 `rules/verification.md`에 정의되어 있다.
이 스킬은 해당 원칙의 **실행 엔진**이다.
---
## Overview
통합 검증 엔진 스킬은 `/handoff-verify` 커맨드의 핵심 동작을 정의한다.
v5의 `/verify` 단독 커맨드에서 v6의 `/handoff-verify` 통합 커맨드로 진화하였다.
핵심 변경: **Task 도구로 verify-agent 서브에이전트를 생성하여 fresh context에서 검증.**
`/clear` 없이도 편향 없는 검증이 가능하다.
---
## Trigger Conditions
### 직접 호출
| 트리거 | 설명 |
|--------|------|
| `/handoff-verify` | 핸드오프 + 기본 루프 검증 (최대 5회) |
| `/handoff-verify --once` | 핸드오프 + 단발 검증 |
| `/handoff-verify --loop 3` | 핸드오프 + 3회 루프 |
| `/handoff-verify --security` | 핸드오프 + 보안 검증 포함 |
| `/handoff-verify --coverage` | 핸드오프 + 테스트 커버리지 분석 |
| `/handoff-verify --extract` | 핸드오프 + 에러 추출/분류 모드 |
| `/handoff-verify --skip-handoff` | 핸드오프 생략 + 검증만 |
### 자동 호출
| 상황 | 동작 |
|------|------|
| `/commit-push-pr` 실행 전 | `--once` 모드로 사전 검증 |
| `/orchestrate` 검증 단계 | 루프 모드로 자동 실행 |
---
## Architecture (v6)
```
/handoff-verify 커맨드 (부모 컨텍스트)
│
├── [1] handoff.md 자동 생성
│ └── git diff 분석, 변경 의도 문서화
│
├── [2] verify-agent 서브에이전트 생성 (Task 도구)
│ └── Fresh context! (/clear 대체)
│ │
│ ├── handoff.md 읽기
│ ├── 검증 파이프라인 실행
│ ├── 실패 시 자동 수정 + 재시도
│ └── 결과 반환
│
└── [3] 결과 수신 및 처리
├── PASS → handoff.md 정리, 다음 단계 안내
└── FAIL → 에러 보고, 권장 조치 안내
```
### v5 대비 아키텍처 변경
| v5 | v6 |
|----|-----|
| /handoff → /clear → /verify | /handoff-verify (단일 커맨드) |
| 부모 컨텍스트에서 직접 검증 | 서브에이전트가 fresh context에서 검증 |
| /clear로 컨텍스트 손실 | 부모 컨텍스트 보존 |
| 수동 3단계 워크플로우 | 자동 1단계 워크플로우 |
---
## Verification Pipeline
### 단계별 실행 순서 (verify-agent 내부)
```
[1단계] 환경 파악
├── handoff.md 읽기 (변경 의도)
├── git status / diff
├── 프로젝트 타입 감지
└── 패키지 매니저 감지
│
[2단계] 빌드 검증
├── npm run build / go build / cargo build
└── 빌드 실패 시 → Fixable 자동 수정
│
[3단계] 타입 검사
├── tsc --noEmit / mypy / go vet
└── 타입 오류 → Fixable 자동 수정
│
[4단계] 린트 검사
├── eslint / golangci-lint / clippy
└── 린트 오류 → Fixable 자동 수정
│
[5단계] 테스트 실행
├── npm test / go test / cargo test
└── 실패 시 → 에러 분석 + 수정 시도
│
[6단계] 코드 리뷰 (effort에 따라)
├── low: 건너뜀
├── medium: 변경 파일만
├── high: 변경 파일 + 의존성
└── max: 전체 영향 분석
│
[7단계] 보안 검토 (--security 또는 effort:max)
└── security-reviewer 서브에이전트 연동
```
### 루프 동작 원리
```
[실행 #1]
│ FAIL → Fixable 자동 수정 → 재실행
│
[실행 #2]
│ FAIL → Fixable 자동 수정 → 재실행
│
[실행 #3~5]From sangrokjung/claude-forge, MIT.
More from sangrokjung/claude-forge
- 0.776score
harness-diet
sangrokjung
Measure and shrink the always-loaded context of a Claude Code harness (CLAUDE.md + rules without paths frontmatter) back under budget — migrate narrative to…
SkillBFreshness: B★ 863Claude Code +9 - 0.776score
skill-factory
sangrokjung
Analyze session work and automatically convert reusable patterns into Claude Code skills.
SkillBFreshness: B★ 863Claude Code +9 - 0.776score
systematic-debugging
sangrokjung
Structured debugging methodology — use before proposing fixes for any error or failure.
SkillBFreshness: B★ 863Claude Code +9 - 0.776score
humanize-korean
sangrokjung
Clean up translation-ese and AI-writing tics in Korean prose so it reads like a person wrote it — content (facts, numbers, proper nouns, quotes) stays 100%…
SkillBFreshness: B★ 863Claude Code +9 - 0.776score
review-loop
sangrokjung
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until…
SkillBFreshness: B★ 863Claude Code +9 - 0.776score
session-wrap
sangrokjung
Use when wrapping up a session before ending.
SkillBFreshness: B★ 863Claude Code +9 - 0.776score
cc-dev-agent
sangrokjung
Use when starting Claude Code projects, writing CLAUDE.md/spec.md, dispatching subagents, or requesting Agent Teams parallel development.
SkillBFreshness: B★ 863Claude Code +9 - 0.776score
relay
sangrokjung
Session relay — compresses what's been done so far (writes a one-liner for /compact) and generates a "next task" prompt (a baton) for the user to hand off.
SkillBFreshness: B★ 863Claude Code +9 - 0.776score
frontend-code-review
sangrokjung
Trigger when the user requests a review of frontend files (e.g., `.tsx`, `.ts`, `.js`).
SkillBFreshness: B★ 863Claude Code +9 - 0.773score
continuous-learning-v2
sangrokjung
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
SkillBFreshness: B★ 863Claude Code +9 - 0.773score
korean-spell-check
sangrokjung
Use Nara/PNU Korean spell-check surfaces conservatively to proofread Korean text, chunk long input, and return change-focused correction suggestions.
SkillBFreshness: B★ 863Claude Code +9 - 0.772score
loop-forge
sangrokjung
Turn a one-line description of a repetitive task into a reusable, self-guarding slash command.
SkillBFreshness: B★ 863Claude Code +9
Signals
- Stars
- 863
- Forks
- 184
- Open issues
- 22
- Last commit (this folder)
- Jun 19, 2026 (4 months ago)
- Last release
- Aug 25, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/sangrokjung/claude-forge
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from sangrokjung
- 0.776score
harness-diet
sangrokjung
Measure and shrink the always-loaded context of a Claude Code harness (CLAUDE.md + rules without paths frontmatter) back under budget — migrate narrative to…
SkillBFreshness: B★ 863Claude Code +9 - 0.776score
relay
sangrokjung
Session relay — compresses what's been done so far (writes a one-liner for /compact) and generates a "next task" prompt (a baton) for the user to hand off.
SkillBFreshness: B★ 863Claude Code +9 - 0.776score
cc-dev-agent
sangrokjung
Use when starting Claude Code projects, writing CLAUDE.md/spec.md, dispatching subagents, or requesting Agent Teams parallel development.
SkillBFreshness: B★ 863Claude Code +9 - 0.776score
frontend-code-review
sangrokjung
Trigger when the user requests a review of frontend files (e.g., `.tsx`, `.ts`, `.js`).
SkillBFreshness: B★ 863Claude Code +9 - 0.776score
humanize-korean
sangrokjung
Clean up translation-ese and AI-writing tics in Korean prose so it reads like a person wrote it — content (facts, numbers, proper nouns, quotes) stays 100%…
SkillBFreshness: B★ 863Claude Code +9 - 0.776score
review-loop
sangrokjung
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until…
SkillBFreshness: B★ 863Claude Code +9
Cite this page
verification-engine skill. Agent Mart. https://agentmart.dev/skills/sangrokjung-verification-engine (last updated 2026-10-24)