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 WYRE-AI/msp-claude-plugins --skill tenantsgit 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/tenants)<a href="https://agentmods.dev/skills/wyre-ai/msp-claude-plugins/tenants"><img src="https://agentmods.dev/badge/skills/wyre-ai/msp-claude-plugins/tenants/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/wyre-ai/msp-claude-plugins/tenants"><img src="https://agentmods.dev/badge/skills/wyre-ai/msp-claude-plugins/tenants.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00060 | $0.00874 |
| Opus 5.5 | $0.00024 | $0.00350 |
| Sonnet 5.5 | $0.00012 | $0.00175 |
| Haiku 4.5 | $0.00006 | $0.00087 |
Grade A, and why
cipp-tenants 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 2mo 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CIPP Tenants
Tenants are the top-level scope in CIPP. Every operational tool — users, mailboxes, standards, security — takes a tenantFilter parameter that scopes the call to one tenant or to allTenants. Knowing how to enumerate tenants and resolve a friendly name to its tenant ID is the first step in almost every CIPP workflow.
Anti-triggers
- Inforcer's tenant list — Inforcer manages the same M365 tenants
but keys them by an integer Client Tenant ID, not a domain or GUID.
A
tenantFiltervalue from here will not work there; useinforcer-tenant-management. - Why a tenant is missing, stale, or failing — that is usually the
GDAP delegation chain, not the tenant record; use
cipp-ops. - A tenant's licence, standards, or CA posture — this skill only
resolves and describes the tenant itself; use
cipp-licenses,cipp-standards, orcipp-security.
Tools
cipp_list_tenants
List every tenant CIPP manages. Returns a list of tenant objects with customerId, defaultDomainName, displayName, and onboarding status.
cipp_list_tenants()
Use this whenever a user refers to a client by name — the response gives you the defaultDomainName (or customerId) needed for tenantFilter on every other tool.
cipp_get_tenant_details
Retrieve detailed information for one tenant: license count, domain list, GDAP relationship status, last refresh time.
cipp_get_tenant_details(tenantFilter='contoso.onmicrosoft.com')
Use tenantFilter='allTenants' to get a portfolio-wide aggregate — useful for fleet reports.
Identifying a tenant
Most CIPP tools accept any of these in tenantFilter:
| Format | Example | Notes |
|---|---|---|
| Default domain | contoso.onmicrosoft.com |
Most readable, recommended |
| Custom domain | contoso.com |
Works if CIPP has it cached |
| Tenant GUID | 00000000-0000-0000-0000-000000000000 |
Most stable but opaque |
allTenants |
allTenants |
Portfolio-wide; only some tools support it |
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.
- 2mo ago First seen · 79 lines · 60 tokens per session scan A 48ca21daa898
cipp-tenants is a skill published in the GitHub repository WYRE-AI/msp-claude-plugins (52 stars, last pushed yesterday), licensed Apache-2.0. It adds 60 tokens to every session and 874 once invoked, about $0.0002 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 2026-09-04.
cipp-tenants compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cipp-tenantsWYRE-AI/msp-claude-plugins | Skill | 52 | yesterday | Apache-2.0 | A | 60 | Claude Code |
| live-previewSethGammon/Citadel | Skill | 927 | yesterday | MIT | A | 40 | Claude Code |
| media-gemini-3-image-promptmodu-ai/moai-cowork | Skill | 315 | 29d ago | Apache-2.0 | A | 329 | Claude Code |
| cs-voc-triagemodu-ai/moai-cowork | Skill | 315 | 29d ago | Apache-2.0 | A | 358 | Claude Code |
| design-copywritingmodu-ai/moai-cowork | Skill | 315 | 29d ago | Apache-2.0 | A | 81 | Claude Code |
| content-card-newsmodu-ai/moai-cowork | Skill | 315 | 29d ago | Apache-2.0 | A | 58 | Claude Code |
| lead-intelligencenaveedharri/benai-skills | Skill | 78 | 28d ago | MIT | A | 150 | Claude Code |