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 agentmods add skills/wyre-ai/msp-claude-plugins/securitynpx skills add WYRE-AI/msp-claude-plugins --skill securitygit clone --depth 1 https://github.com/WYRE-AI/msp-claude-pluginsWrote 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/wyre-ai/msp-claude-plugins/security)<a href="https://agentmods.dev/skills/wyre-ai/msp-claude-plugins/security"><img src="https://agentmods.dev/badge/skills/wyre-ai/msp-claude-plugins/security.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 | $0.00050 | $0.00992 |
| Opus 5 | $0.00025 | $0.00496 |
| Sonnet 5 | $0.00010 | $0.00198 |
| Haiku 4.5 | $0.00005 | $0.00099 |
Grade A, and why
cipp-security 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 yesterday.
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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CIPP Security — Conditional Access & Named Locations
Read-only access to a tenant's Conditional Access policy graph and named-location list. Use as input to security posture reviews and to detect tenants drifting from MSP baseline policies. CIPP doesn't expose CA write operations through MCP — apply policy changes via CIPP standards or the CIPP UI.
Anti-triggers
- Creating, editing, or deploying a CA policy — there is no CA
write tool here; policy rollout goes through
cipp-standardsor the CIPP UI. - Who has actually registered MFA — CA tells you what is required,
not what users have enrolled;
cipp_list_mfa_usersincipp-usersanswers the enrolment question. - Defender, secure score, or threat policies for one tenant you hold
credentials for — that is the
m365plugin'sMicrosoft 365 Security; this skill is CSP-delegated and CA-only. - Portfolio-wide posture scoring — comparing tenants against a
baseline template is
cipp-standardsorinforcer-compliance-reporting.
Tools
cipp_list_conditional_access_policies
cipp_list_conditional_access_policies(tenantFilter='contoso.onmicrosoft.com')
Returns every CA policy with displayName, state (enabled / disabled / enabledForReportingButNotEnforced), conditions (users, apps, locations, platforms, sign-in risk), and grantControls (MFA, compliant device, terms of use, etc).
cipp_list_named_locations
cipp_list_named_locations(tenantFilter='contoso.onmicrosoft.com')
Returns named locations: IP ranges (trusted/untrusted) and country-based locations. These are the building blocks CA policies reference for location-based controls.
What to look for in a CA review
| Finding | Why it matters |
|---|---|
Zero policies in enabled state |
Tenant has no CA enforcement at all — a baseline enabledForReportingButNotEnforced doesn't block anything |
| MFA not required for "All cloud apps" | A baseline policy is missing or scoped too narrowly |
| Policies excluding the entire admin role | Common configuration mistake; admins should require more MFA, not less |
| Trusted location includes home/coffee-shop IPs | Named-location bloat creates exception paths for attackers |
legacy authentication not blocked |
Basic auth bypasses MFA entirely; should be blocked tenant-wide |
| Reporting-only policies older than 30 days | Should have been promoted to enabled or removed |
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.
- yesterday First seen · 83 lines · 50 tokens per session scan A 2f79251ac5e2
cipp-security is a skill published in the GitHub repository WYRE-AI/msp-claude-plugins (44 stars, last pushed 2d ago), licensed Apache-2.0. It adds 50 tokens to every session and 992 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 2026-09-04.
Other skills, from other repositories
review
5-pass structured code review — correctness, security, performance, readability, consistency.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
design-copywriting
마케팅·제품 텍스트의 브랜드 정합 카피라이팅 전문가. 브랜드 보이스, AI 특유 어조 배제 규칙, 구체적 숫자, 다운스트림 에이전트 소비를 위한 JSON 섹션 구조를 보장합니다. 히어로, 기능, 소셜 증명, CTA, 푸터 섹션을 A/B 변형 출력으로 다룹니다. Use for brand-aligned marketing and product copy: headlines, CTAs, microcopy, taglines, value propositions, marketing-landing-page and footer copy, with anti-AI-slop rules…
content-card-news
인스타그램·스레드·카카오 채널용 카드뉴스 4장(본문 카피·디자인 가이드·이미지 생성 프롬프트·채널별 캡션·해시태그)을 한 번에 만들어 드립니다. 다음과 같은 요청 시 사용하세요: "카드뉴스 만들어줘" "인스타 슬라이드 기획해줘" "캐러셀 콘텐츠 구성해줘" "재택근무 도구 비교 카드뉴스 만들어줘" "스타트업 시드 라운드 체크리스트 카드뉴스 써줘" "프롬프트 엔지니어링 FAQ 카드뉴스 기획해줘" 주제에 맞는 구성 패턴을 자동으로 골라 4장을 채우고, 이미지 생성은 moai-coworker 이미지 스킬로, 한국어 자연화는…
media-gemini-3-image-prompt
Google Gemini 3 Pro Image (a.k.a. Nano Banana Pro) 전용 이미지 프롬프트 빌더. 사용자 자연어 한 줄 + AskUserQuestion 프리셋·미세조정으로 컨텍스트를 수집해 Google AI Developers 공식 가이드의 5-component 구조([Subject+Adj] doing [Action] in [Location]. [Composition]. [Lighting]. [Style]. [Constraint/Text])로 변환합니다. Google AI Studio · Vertex AI · Gemini 앱에 그대로 복붙…
cs-voc-triage
고객의 소리(VOC) 전체를 다루는 엄브렐러 스킬 — 멀티채널 리뷰를 통합 분석하고(리뷰는 VOC의 한 원천), 폭주하는 VOC의 처리 우선순위를 3축 분류 + KTAS 응급실 5단계로 판별합니다. 다음과 같은 요청 시 반드시 이 스킬을 사용하세요: "리뷰 모아서 분석해줘", "리뷰 분석해줘", "수백 개 리뷰 정리", "감정 분석 리뷰", "쿠팡 리뷰 키워드", "리뷰 인사이트 액션플랜", "멀티채널 리뷰 통합", "VOC 분류해줘", "VOC 처리 순서", "고객 문의 우선순위", "응급 VOC 분류", "VOC 트리아지", "KTAS 응급실 분류 VOC" 2개…