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 magnusfroste/flowwink --skill copilot-builder-as-mcpgit clone --depth 1 https://github.com/magnusfroste/flowwinkWrote 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/magnusfroste/flowwink/copilot-builder-as-mcp)<a href="https://agentmods.dev/skills/magnusfroste/flowwink/copilot-builder-as-mcp"><img src="https://agentmods.dev/badge/skills/magnusfroste/flowwink/copilot-builder-as-mcp/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/magnusfroste/flowwink/copilot-builder-as-mcp"><img src="https://agentmods.dev/badge/skills/magnusfroste/flowwink/copilot-builder-as-mcp.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 | $0.00041 | $0.00325 |
| Opus 5.5 | $0.00016 | $0.00130 |
| Sonnet 5.5 | $0.00008 | $0.00065 |
| Haiku 4.5 | $0.00004 | $0.00032 |
Grade A, and why
copilot-builder-as-mcp-skill 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 1mo 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
Copilot Builder as First-Class MCP Skill
copilot-action powers the admin /admin/copilot site-builder UI (block-by-block
migration & site generation with create_block / migrate_url / update_footer /
activate_modules tool calls). It is now ALSO exposed as the MCP skill
build_site_step (handler edge:copilot-action, scope both, mcp_exposed=true,
category content, owned by pages module).
One implementation, two consumers:
- Internal:
useCopilot.ts→supabase.functions.invoke('copilot-action', …) - External: any MCP client →
build_site_steptool
The skill is stateless — caller owns conversation history. Loop:
- POST
messages: [{role, content}], currentModules?, migrationState? - Receive
{ message, toolCall? } - Apply toolCall (caller's responsibility — for external claws this typically
means chaining to
migrate_url,create_page_block,manage_global_blocks). - Append result as next user message; repeat until no toolCall.
Registered in src/lib/modules/pages-module.ts skillSeeds + agent_skills row
seeded via migration 20260504185230_*.
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.
- 1mo ago First seen · 28 lines · 41 tokens per session scan A 406fd5a7351c
copilot-builder-as-mcp-skill is a skill published in the GitHub repository magnusfroste/flowwink (26 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 325 once invoked, about $0.0002 per session on Opus 5.5. 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
payload
Use when working with Payload projects (payload.config.ts, collections, fields, hooks, access control, Payload API). Use when debugging validation errors, security issues, relationship queries, transactions, or hook behavior.
getting-started
Get started with your Open SaaS project — fetches docs, checks Wasp installation, and helps you start your database and app.
guided-tour
Take a guided tour of Open SaaS — walks you through step-by-step through the project structure, features, and customization checklist.
add-wasp-skills
Install Wasp agent skills (plugins) that add Wasp knowledge and best practices to your AI coding tools.
luxury
Minimalist high-fashion design with editorial serif headlines, ivory and near-black palette, antique gold accents, sharp edges and generous whitespace.
pagible
Dark, immersive design with blue-purple gradient accents, sharp edges, and a deep navy background for a modern tech aesthetic.