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 Mumega-com/mcpwp-claude-plugin --skill connectgit clone --depth 1 https://github.com/Mumega-com/mcpwp-claude-pluginWrote 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/mumega-com/mcpwp-claude-plugin/connect)<a href="https://agentmods.dev/skills/mumega-com/mcpwp-claude-plugin/connect"><img src="https://agentmods.dev/badge/skills/mumega-com/mcpwp-claude-plugin/connect.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 | $0.00032 | $0.00754 |
| Opus 5 | $0.00016 | $0.00377 |
| Sonnet 5 | $0.00006 | $0.00151 |
| Haiku 4.5 | $0.00003 | $0.00075 |
Grade B, and why
connect scanned grade B with 1 finding 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 8d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
**Global** (`~/.claude/settings.json`): The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 8d ago First seen · 99 lines · 32 tokens per session scan B 491e30c2f372
connect is a skill published in the GitHub repository Mumega-com/mcpwp-claude-plugin (4 stars, last pushed 3mo ago), with no licence file. It adds 32 tokens to every session and 754 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
elementor-to-generateblocks
Convert Elementor layouts to clean GenerateBlocks V2 format, eliminating DIVception.
elementor-v3-builder
Stonewright Elementor V3 builder for native-first implementation from Figma, screenshots, images, or briefs, plus pages, widgets, Loop Grid, templates, kit styles, responsive edits, and safe batch mutations. Use whenever a task reads, plans, builds, or repairs an Elementor V3 page or template.
gutenberg-fse-builder
Stonewright Gutenberg and FSE builder. Inserts/updates blocks, manages theme.json global styles, FSE templates, template parts, and synced patterns.
blocksy-build-page
Use when building Blocksy pages with live block schemas, theme chrome tokens, and the Gutenberg finalizer.
design-to-wordpress
Stonewright Figma/image/brief → DesignEvidence → native plan → Elementor / Gutenberg / FSE apply → agent-owned Playwright verification loop.
generateblocks-build-page
Use when building pages with GenerateBlocks, live generateblocks/ schemas, and GeneratePress chrome when that theme is active.