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.
npx skills add sangrokjung/claude-forge --skill verification-enginegit clone --depth 1 https://github.com/sangrokjung/claude-forgeWrote 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.
[](https://agentmods.dev/skills/sangrokjung/claude-forge/verification-engine)<a href="https://agentmods.dev/skills/sangrokjung/claude-forge/verification-engine"><img src="https://agentmods.dev/badge/skills/sangrokjung/claude-forge/verification-engine.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00052 | $0.02366 |
| Opus 5 | $0.00026 | $0.01183 |
| Sonnet 5 | $0.00010 | $0.00473 |
| Haiku 4.5 | $0.00005 | $0.00237 |
Grade A, and why
verification-engine 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
검증 원칙
Iron Law, Gate Function, Common Failures 체크리스트는 rules/verification.md에 정의되어 있다.
이 스킬은 해당 원칙의 실행 엔진이다.
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
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.
- 3d ago First seen · 260 lines · 52 tokens per session scan A 26321e6f5e2f
verification-engine is a skill published in the GitHub repository sangrokjung/claude-forge (824 stars, last pushed 3d ago), licensed MIT. It adds 52 tokens to every session and 2,366 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.
Other skills, from other repositories
test-fixing
Run tests and systematically fix all failing tests using smart error grouping. Use when user asks to fix failing tests, mentions test failures, runs test suite and failures occur, or requests to make tests pass.
accessibility-a11y
WCAG 2.2 compliance, ARIA patterns, keyboard navigation, screen readers, automated testing.
browser-qa-report
Runs a read-only browser QA pass and returns evidence.
page-benchmark-report
Collects a small repeated benchmark for a page using Friday's readonly browser runtime.
api-integration-test
Create, maintain, and run gated Go integration tests for internal APIs and service-to-service clients (HTTP/gRPC). Use for endpoint verification, contract checks with real runtime config, opt-in execution, timeout/retry safety, and integration failure triage in Go services.
unit-test
A Go testing workflow for writing unit tests: small tests that check individual functions or components. It supports table-driven cases, where many inputs and expected results are organised in one test, and subtests.