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.
git 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/plugins/wyre-ai/msp-claude-plugins/cipp)<a href="https://agentmods.dev/plugins/wyre-ai/msp-claude-plugins/cipp"><img src="https://agentmods.dev/badge/plugins/wyre-ai/msp-claude-plugins/cipp/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/plugins/wyre-ai/msp-claude-plugins/cipp"><img src="https://agentmods.dev/badge/plugins/wyre-ai/msp-claude-plugins/cipp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
cipp 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 4d 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.
What it actually says
{
"name": "cipp",
"version": "0.1.10",
"description": "Claude plugins for CIPP (CyberDrain Improved Partner Portal) \u2014 Microsoft 365 multi-tenant management for MSPs: tenants, users, mailboxes, conditional access, standards, BPA, licensing, GDAP, and alerts",
"author": {
"name": "MSP Claude Plugins Community"
},
"homepage": "https://github.com/wyre-technology/msp-claude-plugins",
"repository": "https://github.com/wyre-technology/msp-claude-plugins",
"license": "Apache-2.0"
}
What it installs
The manifest is a name and a version. 7 skills, 4 commands, 2 agents travel with it, and installing the plugin installs all of them — 783 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill cipp-licenses A 54 tokens
- Skill cipp-mailboxes A 51 tokens
- Skill cipp-ops A 48 tokens
- Skill cipp-standards A 59 tokens
- Skill cipp-groups A 61 tokens
- Skill cipp-security A 50 tokens
- Skill cipp-tenants A 60 tokens
- Command offboard-user A 27 tokens
- Command standards-drift A 28 tokens
- Command secure-score-report A 28 tokens
- Command tenant-health A 23 tokens
- Agent user-offboarding-runner A 166 tokens
- Agent security-posture-reviewer A 128 tokens
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.
- 4d ago Changed 826c20096828
- 16d ago Changed beafc3e0131e
- 27d ago Changed 58812777bd1b
- 2mo ago First seen · 12 lines scan A b5722ea82376
cipp is a plugin published in the GitHub repository WYRE-AI/msp-claude-plugins (52 stars, last pushed yesterday), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 compared with plugins from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cippWYRE-AI/msp-claude-plugins | Plugin | 52 | yesterday | Apache-2.0 | A | — | Claude Code |
| backend-architectcomposio-community/awesome-claude-plugins | Plugin | 2.0k | 2d ago | none | A | — | Claude Code |
| mcp-buildercomposio-community/awesome-claude-plugins | Plugin | 2.0k | 2d ago | none | A | — | Claude Code |
| opsagent-shopifyMSApps-Mobile/claude-plugins | Plugin | 10 | yesterday | MIT | A | — | Claude Code |
| rad-fastifyRadOrigin-LLC/RAD-Claude-Skills | Plugin | 5 | 2mo ago | Apache-2.0 | A | — | Claude Code |
| vibe-stackOneWave-AI/open-agent-stack | Plugin | 5 | 2mo ago | MIT | A | — | Claude Code |
| java-springducpm2303/claude-java-plugins | Plugin | 17 | 7mo ago | none | A | — | Claude Code |