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 verify-implementationgit 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/verify-implementation)<a href="https://agentmods.dev/skills/sangrokjung/claude-forge/verify-implementation"><img src="https://agentmods.dev/badge/skills/sangrokjung/claude-forge/verify-implementation/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.
<a href="https://agentmods.dev/skills/sangrokjung/claude-forge/verify-implementation"><img src="https://agentmods.dev/badge/skills/sangrokjung/claude-forge/verify-implementation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 302 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 303 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00037 | $0.02797 |
| Opus 5.5 | $0.00015 | $0.01119 |
| Sonnet 5.5 | $0.00007 | $0.00559 |
| Haiku 4.5 | $0.00004 | $0.00280 |
Grade A, and why
verify-implementation 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 1mo 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 — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
구현 검증
목적
프로젝트에 등록된 모든 verify-* 스킬을 실행하여 통합 패턴 검증을 수행합니다:
- 각 스킬의 Workflow에 정의된 검사를 실행
- 각 스킬의 Exceptions를 참조하여 false positive 방지
- 발견된 이슈에 severity 레벨 분류
- 사용자 승인 후 수정 적용 및 재검증
verification-engine과의 역할 구분
| 항목 | verification-engine | verify-implementation (이 스킬) |
|---|---|---|
| 대상 | 기술 검증 (빌드, 타입, 린트, 테스트) | 패턴 검증 (코딩 규칙, 아키텍처 패턴, 프로젝트 규약) |
| 트리거 | /handoff-verify |
/verify-implementation |
| 자동 수정 | Fixable 9종 즉시 수정 | 사용자 승인 후 수정 (기본) 또는 --fix로 자동 |
두 시스템은 상호보완입니다. 기술 검증은 verification-engine에, 패턴 검증은 이 스킬에 위임합니다.
실행 시점
- 새로운 기능을 구현한 후
- Pull Request를 생성하기 전
- 코드 리뷰 중
- 코드베이스 규칙 준수 여부를 감사할 때
/handoff-verify통과 후 패턴 준수 추가 확인 시
실행 플래그
| 플래그 | 설명 | 기본값 |
|---|---|---|
--fix |
발견 이슈 자동 수정 (사용자 확인 없이) | OFF |
--report-only |
보고서만 생성, 수정 제안 없음 | OFF |
--severity <level> |
특정 심각도 이상만 보고 (CRITICAL/HIGH/MEDIUM/LOW) | LOW (전체) |
--category <name> |
특정 verify-* 스킬만 실행 (예: --category api) |
전체 |
심각도 레벨
| 레벨 | 설명 | 예시 |
|---|---|---|
| CRITICAL | 즉시 수정 필수. 배포 차단 | 인증 없는 API 엔드포인트, 하드코딩된 시크릿 |
| HIGH | PR 전 수정 권장 | 패턴 위반, 누락된 유효성 검사 |
| MEDIUM | 수정 권장하나 긴급하지 않음 | 네이밍 규칙 불일치, 불필요한 코드 |
| LOW | 개선 제안 | 더 나은 패턴 존재, 문서 보강 필요 |
실행 대상 스킬
이 스킬이 실행하는 검증 스킬 목록입니다. /manage-skills가 스킬을 생성/삭제할 때 이 목록을 자동 업데이트합니다.
| # | 스킬 | 설명 |
|---|---|---|
(프로젝트에서 /manage-skills로 생성됨) |
(프로젝트별 verify-* 스킬은 각 프로젝트에서 동적으로 생성됩니다) | (프로젝트 지침을 참조하세요) |
워크플로우
Step 1: 소개 및 실행 전략 결정
위의 실행 대상 스킬 섹션에 나열된 스킬을 확인합니다.
선택적 인수가 제공된 경우:
- 특정 스킬 이름 -> 해당 스킬만 필터링
--category <name>->verify-<name>*패턴과 매칭되는 스킬만 필터링--severity <level>-> 모든 스킬 실행 후 해당 심각도 이상만 보고
등록된 스킬이 0개인 경우:
## 구현 검증
검증 스킬이 없습니다. `/manage-skills`를 실행하여 프로젝트에 맞는 검증 스킬을 생성하세요.
이 경우 워크플로우를 종료합니다.
등록된 스킬이 1개 이상인 경우:
적응형 실행 전략 결정
IF 실행 대상 스킬 수 <= 5:
-> 순차 실행 (토큰 절약, 컨텍스트 내 직접 실행)
ELSE IF 실행 대상 스킬 수 >= 6:
-> 병렬 실행 (Task 서브에이전트, fresh context)
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.
- 1mo ago First seen · 306 lines · 37 tokens per session scan A f4ba83efe52a
verify-implementation is a skill published in the GitHub repository sangrokjung/claude-forge (863 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 2,797 once invoked, about $0.0001 per session on Opus 5.5. 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
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.
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.
e2e-test
Design, maintain, and execute reliable end-to-end tests for critical user journeys with Agent Browser as first choice for exploration and Playwright as the preferred code path for suites and CI. Use for E2E strategy, journey coverage, flaky test triage, artifact collection, CI gating, regression prevention, and…
fuzzing-test
A Go testing guide for generating fuzz tests, which repeatedly try varied inputs to find crashes and unexpected behavior. It first checks whether the code is suitable for fuzzing.
go-code-reviewer
Review Go code with a defect-first approach using repository policy (constitution.md first, then AGENTS.md fallback). Use for code review, PR review, quality checks, risk analysis, and regression detection.
go-review-lead
Orchestrate a comprehensive Go code review by triaging code changes, dispatching vertical review skills (security, concurrency, error, logic, performance, quality, test, observability) as parallel agents, then consolidating results into a unified report. Use for full Go PR review or comprehensive code review. Replaces…