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 manage-skillsgit 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/manage-skills)<a href="https://agentmods.dev/skills/sangrokjung/claude-forge/manage-skills"><img src="https://agentmods.dev/badge/skills/sangrokjung/claude-forge/manage-skills/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/manage-skills"><img src="https://agentmods.dev/badge/skills/sangrokjung/claude-forge/manage-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 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 378 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 379 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 381 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 | $0.00054 | $0.05000 |
| Opus 5 | $0.00027 | $0.02500 |
| Sonnet 5 | $0.00011 | $0.01000 |
| Haiku 4.5 | $0.00005 | $0.00500 |
Grade A, and why
manage-skills 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 7d 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 — 410 lines — stays where its author put it; the contents beside it link to each section on GitHub.
세션 기반 스킬 유지보수
목적
현재 세션에서 변경된 내용을 분석하여 검증 스킬의 드리프트를 탐지하고 수정합니다:
- 커버리지 누락 -- 어떤 verify 스킬에서도 참조하지 않는 변경된 파일
- 유효하지 않은 참조 -- 삭제되거나 이동된 파일을 참조하는 스킬
- 누락된 검사 -- 기존 검사에서 다루지 않는 새로운 패턴/규칙
- 오래된 값 -- 더 이상 일치하지 않는 설정값 또는 탐지 명령어
글로벌 스킬 특성
이 스킬은 ~/.claude/skills/에 설치된 글로벌 스킬입니다.
프로젝트별 verify-* 스킬은 각 프로젝트의 .claude/skills/에 생성됩니다.
등록 테이블은 프로젝트별 CLAUDE.md에서 관리합니다.
스킬 위치 규칙
| 스킬 유형 | 위치 | 이유 |
|---|---|---|
| manage-skills (이 스킬) | ~/.claude/skills/ |
모든 프로젝트에서 공통 사용 |
| verify-implementation | ~/.claude/skills/ |
모든 프로젝트에서 공통 사용 |
| verify-* (검증 스킬) | 프로젝트 .claude/skills/ |
프로젝트별 규칙/패턴 |
실행 시점
- 새로운 패턴이나 규칙을 도입하는 기능을 구현한 후
- 기존 verify 스킬을 수정하고 일관성을 점검하고 싶을 때
- PR 전에 verify 스킬이 변경된 영역을 커버하는지 확인할 때
- 검증 실행 시 예상했던 이슈를 놓쳤을 때
- 주기적으로 스킬을 코드베이스 변화에 맞춰 정렬할 때
등록된 검증 스킬
현재 프로젝트에 등록된 검증 스킬 목록입니다. 새 스킬 생성/삭제 시 이 목록을 업데이트합니다.
참고: 이 테이블은 글로벌 레벨의 기본값입니다. 실제 프로젝트별 등록은 프로젝트 CLAUDE.md의
## Verify Skills섹션에서 관리됩니다.
| 스킬 | 설명 | 커버 파일 패턴 |
|---|---|---|
(프로젝트에서 /manage-skills로 생성됨) |
(프로젝트 지침에 맞는 스킬을 생성하려면 /manage-skills를 실행하세요) |
(자동으로 결정됨) |
에이전트 중복 감지 (CRITICAL)
verify-* 스킬을 생성하기 전에 기존 전문 에이전트가 해당 도메인을 이미 커버하는지 확인합니다. 중복 생성은 토큰 낭비이며 결과 충돌을 유발합니다.
에이전트-도메인 매핑
| 기존 에이전트 | 커버 도메인 | verify-* 스킬 생성 금지 |
|---|---|---|
| security-reviewer | 보안 취약점, OWASP, CWE | verify-security, verify-auth-security |
| database-reviewer | DB 스키마, 쿼리 최적화, 마이그레이션 | verify-db, verify-schema, verify-migration |
| code-reviewer | 코드 품질, 네이밍, 복잡도 | verify-code-quality, verify-naming |
| build-error-resolver | 빌드 오류, 타입 오류 | verify-build, verify-types |
| e2e-runner | E2E 테스트 | verify-e2e |
판단 기준
새 verify-* 스킬 생성 요청 시:
IF 위 에이전트-도메인 매핑에 해당하는 경우:
→ SKIP: "이 도메인은 {에이전트명} 에이전트가 담당합니다" 안내
ELSE IF 에이전트가 일부만 커버하는 경우:
→ 에이전트가 커버하지 않는 부분만 verify-* 스킬로 생성
ELSE:
→ 정상 생성 진행
워크플로우
Step 1: 세션 변경사항 분석
현재 세션에서 변경된 모든 파일을 수집합니다:
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.
- 7d ago First seen · 410 lines · 54 tokens per session scan A 3e745d374bca
manage-skills is a skill published in the GitHub repository sangrokjung/claude-forge (835 stars, last pushed 8d ago), licensed MIT. It adds 54 tokens to every session and 5,000 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
incident-postmortem
Incident post-mortem specialist for writing blameless post-mortems, extracting timelines from logs/events, conducting root cause analysis (5-Why, fishbone), classifying severity, and generating tracked action items. ALWAYS use when writing a post-mortem, reviewing an incident, extracting a timeline, performing root…
log-analyzer
Senior-SRE log analysis specialist. Use when investigating incidents from logs, triaging error spikes, extracting timelines, correlating distributed traces, or separating signal from noise across plain-text, JSON (slog/zap), syslog, journald, container, and Kubernetes logs. ALWAYS use when the user asks to "analyze…
systematic-debugging
Use when debugging, diagnosing, or investigating any bug, test failure, flaky test, race condition, unexpected behavior, build failure, production incident, third-party breakage, root cause analysis, or performance regression before proposing fixes.
debug-systematic
Systematic 4-phase debugging methodology for complex, intermittent, or mysterious issues. Use when investigating bugs, race conditions, or unexplained failures.
stock-analysis-lead
Orchestrate a US-stock investment analysis — classify sector archetype, fetch SEC filings, dispatch a tiered fan-out of six vertical equity-research agents (business model, earnings quality, balance sheet, management, industry, peer comparison) over a validated JSON findings contract, then synthesize a buy/hold/sell…
kafka-event-driven-design
Kafka event-driven architecture designer and reviewer, at the application/client layer. ALWAYS use when designing, reviewing, or troubleshooting how a service produces or consumes Kafka events — topic and partition-key design, producer and consumer client configuration, consumer group topology, event schema definition…