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 Josh-E-S/pexip-mgmt-mcp --skill pexip-mgmt-intakegit clone --depth 1 https://github.com/Josh-E-S/pexip-mgmt-mcpWrote 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/josh-e-s/pexip-mgmt-mcp/pexip-mgmt-intake)<a href="https://agentmods.dev/skills/josh-e-s/pexip-mgmt-mcp/pexip-mgmt-intake"><img src="https://agentmods.dev/badge/skills/josh-e-s/pexip-mgmt-mcp/pexip-mgmt-intake/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/josh-e-s/pexip-mgmt-mcp/pexip-mgmt-intake"><img src="https://agentmods.dev/badge/skills/josh-e-s/pexip-mgmt-mcp/pexip-mgmt-intake.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00143 | $0.01788 |
| Opus 5 | $0.00072 | $0.00894 |
| Sonnet 5 | $0.00029 | $0.00358 |
| Haiku 4.5 | $0.00014 | $0.00179 |
Grade A, and why
pexip-mgmt-intake 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 10d 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pexip management intake
A management-side Pexip task can be many shapes: a one-off operator action ("kick this person"), a recurring report ("daily call volume"), a configuration push ("add 50 VMRs"), an integration extension ("build a webhook receiver"), or a developer task on the MCP server itself ("add a tool for X"). The right skill set, dependencies, and operational stance differ a lot.
Don't guess. Ask a small number of targeted questions, then route.
Keep it brief. Most management tasks resolve in 2-3 questions.
When to use
- Any "I want to use Pexip's management API to…" type request
- Any "automate" / "report" / "monitor" Pexip request without scope
- The user mentioned Pexip and the MCP server but not what they're trying to do
When NOT to use
- Narrow API questions: "what's the schema for
conference?" → answer withpexip-config-api - Live operator verbs: "kick Alice", "lock the AllHands" → answer with
pexip-operations - Specific tool questions: "how do I call
summarize_calls?" → answer withpexip-operations - MCP server code edits: "add a tool that wraps X" → answer with the matching
pexip-*-apideveloper-reference skill
The minimum questions
Ask one at a time, with options where possible. Stop as soon as you have enough to route.
Q1. What are you trying to do? (always ask)
A) One-off operator action against a live or recent meeting
(kick, lock, transfer, change layout, check who's in)
B) Recurring reporting or monitoring
(daily / weekly call volume, quality forensics, alarm dashboard)
C) Bulk configuration change
(create N VMRs, update dial-plan rules, manage end users)
D) Extend the MCP server itself
(add a new tool, wrap a Pexip endpoint not currently covered)
E) Build a webhook receiver for Pexip events
(event sinks pushing to a custom HTTP listener)
F) Integrate Pexip with a room system (MJX / One-Touch Join)
G) Other — please describe
Routing:
- A →
pexip-operations(operator runbook, all live-meeting playbooks) - B →
pexip-operations→reporting.md(orplatform-health.mdfor alarm-style monitoring) - C →
pexip-operations→vmr-administration.mdand / ordial-plan.md - D → the matching developer-reference skill:
- Configuration CRUD →
pexip-config-api - Live state reads →
pexip-status-api - CDR / history reads →
pexip-history-api - Live commands (kick/lock/transfer) →
pexip-command-api
- Configuration CRUD →
- E →
pexip-event-sinks - F →
pexip-mjx - G → ask follow-up
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.
- 10d ago First seen · 184 lines · 143 tokens per session scan A a1a886d537a3
pexip-mgmt-intake is a skill published in the GitHub repository Josh-E-S/pexip-mgmt-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 143 tokens to every session and 1,788 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…