Borrowing it
Nothing to install: this file belongs to devjourney/unifi-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/devjourney/unifi-mcp/main/.agents/skills/claude-plugin-config-transport/SKILL.mdgit clone --depth 1 https://github.com/devjourney/unifi-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/devjourney/unifi-mcp/claude-plugin-config-transport)<a href="https://agentmods.dev/skills/devjourney/unifi-mcp/claude-plugin-config-transport"><img src="https://agentmods.dev/badge/skills/devjourney/unifi-mcp/claude-plugin-config-transport/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/devjourney/unifi-mcp/claude-plugin-config-transport"><img src="https://agentmods.dev/badge/skills/devjourney/unifi-mcp/claude-plugin-config-transport.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 | $0.00192 | $0.05007 |
| Opus 5 | $0.00096 | $0.02504 |
| Sonnet 5 | $0.00038 | $0.01001 |
| Haiku 4.5 | $0.00019 | $0.00501 |
Grade A, and why
myco:claude-plugin-config-transport 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.
This is a copy
100% identical to myco:claude-plugin-config-transport — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Plugin Configuration and Transport Stability
This skill covers the full lifecycle of Claude MCP plugin integration in unifi-mcp: from configuring transport flags correctly, through understanding the asyncio transport architecture that keeps MCP tools available, to verifying plugin setup, writing portable shell scripts, and publishing plugin-only releases. The procedures share a common prerequisite — understanding the uvx launch context — because a wrong flag can trigger a transport race that silently drops all MCP tools with no visible error.
Relevant files:
apps/network/src/unifi_network_mcp/config/config.yamlapps/protect/src/unifi_protect_mcp/config/config.yamlapps/access/src/unifi_access_mcp/config/config.yamlplugins/unifi-network/scripts/set-env.sh,plugins/unifi-network/scripts/check-prereqs.shplugins/unifi-protect/scripts/set-env.sh,plugins/unifi-protect/scripts/check-prereqs.shplugins/unifi-access/scripts/set-env.sh,plugins/unifi-access/scripts/check-prereqs.shpackages/unifi-mcp-shared/src/unifi_mcp_shared/transport.pypackages/unifi-mcp-shared/src/unifi_mcp_shared/strict_dispatch.py.agents/plugins/marketplace.json(multi-target plugin registry: Claude, Codex, OpenClaw).codex-plugin/(Codex-specific manifest directory, PR #246).agents/plugins/openclaw/(OpenClaw-specific manifest directory, PR #248)
Prerequisites
Before modifying any plugin configuration or transport code:
- Understand the uvx launch context. When Claude launches a plugin via
uvx, the plugin process is not PID 1. This distinction controls which transport path activates insidetransport.pyand whether HTTP transport will be enabled. The PID check is inresolve_http_config()intransport.py. - Know all three app directories. Transport and HTTP config changes almost always need to be reflected in
apps/network/,apps/protect/, andapps/access/in parallel. Partial application leaves inconsistent behavior. - Know all three plugin directories. Script and setup changes apply to
plugins/unifi-network/,plugins/unifi-protect/, andplugins/unifi-access/. Applying to only one or two creates inconsistent behavior that is nearly impossible for users to diagnose. - Know the multi-target plugin registry and all three runtimes. As of PR #246 (Codex) and PR #248 (OpenClaw), unifi-mcp supports three plugin targets: Claude, Codex, and OpenClaw. Plugin configuration, version sync, and release procedures must account for target-specific manifests and initialization paths.
- Hold the current MCP shared package version. Plugin versions are slaved to MCP package tags; know the current tag before planning a release (see Procedure F).
- Run
check-prereqs.shfirst (see Procedure D) before activating any plugin setup change in a live environment.
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 · 358 lines · 192 tokens per session scan A 27f09dc49d38
myco:claude-plugin-config-transport is a skill published in the GitHub repository devjourney/unifi-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 192 tokens to every session and 5,007 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to myco:claude-plugin-config-transport, differing in 6 lines, and is treated as a copy.
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…