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 opsgit 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/ops)<a href="https://agentmods.dev/skills/wyre-ai/msp-claude-plugins/ops"><img src="https://agentmods.dev/badge/skills/wyre-ai/msp-claude-plugins/ops.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 | $0.00048 | $0.01220 |
| Opus 5 | $0.00024 | $0.00610 |
| Sonnet 5 | $0.00010 | $0.00244 |
| Haiku 4.5 | $0.00005 | $0.00122 |
Grade A, and why
cipp-ops 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 2d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CIPP Operations
The meta-layer — tools for managing CIPP itself rather than the tenants it manages. GDAP for the delegation chain, scheduler for recurring jobs, and health/version/log endpoints for verifying CIPP is reachable and functioning.
Anti-triggers
- "Who did what" inside a customer tenant —
cipp_list_logshere is CIPP's own application log, not the M365 unified audit log. The near-identically namedcipp_list_audit_logslives incipp-alerts; loading the wrong one is the most common CIPP mis-route. - Entra role assignments inside a tenant — GDAP roles are what the
partner may delegate, a different object from the roles a tenant's
own users hold; use
inforcer-identity-governanceor them365plugin. - Forcing a standards evaluation now — the CIPP scheduler runs it
on a recurrence, but the on-demand call is
cipp_run_standards_checkincipp-standards.
GDAP
cipp_list_gdap_roles
cipp_list_gdap_roles()
Returns the GDAP (Granular Delegated Admin Privileges) role definitions available — the AAD roles your CSP relationship can grant to your MSP technicians per-tenant.
cipp_list_gdap_invites
cipp_list_gdap_invites()
Returns pending GDAP relationship invites that customers have not yet accepted. Stale invites > 14 days are usually customers who lost the email — re-send via the CIPP UI.
GDAP is the modern replacement for AOBO/DAP. Each invite grants the MSP partner tenant a specific set of AAD roles in the customer tenant for a fixed duration. CIPP relies on active GDAP relationships for nearly every multi-tenant operation; broken GDAP = silent failures across the rest of the toolkit.
Scheduler
cipp_list_scheduled_items
cipp_list_scheduled_items()
Lists CIPP's scheduled tasks: recurring standards checks, BPA refreshes, alert evaluations, custom user-defined schedules.
cipp_add_scheduled_item
cipp_add_scheduled_item(name, command, parameters?, recurrence?, scheduledTime?)
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.
- 2d ago First seen · 131 lines · 48 tokens per session scan A 84b61a044fb4
cipp-ops is a skill published in the GitHub repository WYRE-AI/msp-claude-plugins (44 stars, last pushed 4d ago), licensed Apache-2.0. It adds 48 tokens to every session and 1,220 once invoked, about $0.0002 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
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.
review
5-pass structured code review — correctness, security, performance, readability, consistency.
design-copywriting
A copywriting workflow for marketing and product pages that uses a brand voice and returns structured text for page sections.
content-card-news
A planning tool for four-card social media carousels on Instagram, Threads, and Kakao Channel, combining card copy, design guidance, image prompts, captions, and hashtags.
cs-voc-triage
A customer-feedback analysis tool that combines reviews and support contacts from multiple channels. VOC means “voice of the customer”: the comments, questions, complaints, and praise customers leave about a business.
data-realestate
A lookup tool for reported South Korean property transactions using Ministry of Land data. It covers sales and rental deals for apartments, officetels, multi-family homes, houses, and commercial or office properties.