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 agentmods add instructions/quantumcodersys/formasty-mcp/gemini-mdgit clone --depth 1 https://github.com/QuantumCoderSys/formasty-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/instructions/quantumcodersys/formasty-mcp/gemini-md)<a href="https://agentmods.dev/instructions/quantumcodersys/formasty-mcp/gemini-md"><img src="https://agentmods.dev/badge/instructions/quantumcodersys/formasty-mcp/gemini-md.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 | $0.00291 | $0.00291 |
| Opus 5 | $0.00146 | $0.00146 |
| Sonnet 5 | $0.00058 | $0.00058 |
| Haiku 4.5 | $0.00029 | $0.00029 |
Grade A, and why
formasty-mcp GEMINI.md 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 2d 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
Formasty MCP for Gemini CLI
Use the configured formasty MCP server to build and operate forms, quizzes, surveys, and response workflows in the authenticated user's Formasty workspaces.
Connection and authentication
- Use the configured Streamable HTTP endpoint at
https://app.formasty.com/api/mcp. - Complete OAuth when Gemini CLI requests authentication. Formasty supports automatic OAuth discovery, dynamic client registration, PKCE, refresh tokens, and revocation.
- Do not ask the user to paste an API key when OAuth is available.
- Never print, commit, or expose access tokens, API keys, response data, or private form URLs.
Safe operating sequence
- Inspect the live Formasty tools before acting.
- List workspaces and use the authenticated user's current workspace permissions.
- Read the current form and draft revision before editing an existing form.
- Keep the latest draft revision across every mutation.
- Validate the draft before publishing.
- Publish, delete, or modify submissions only when the user's request clearly authorizes it.
- Keep consequential MCP tool calls subject to Gemini CLI's confirmation flow.
Formasty's workspace roles, OAuth scopes, plan limits, optimistic draft revisions, and server-side validation remain authoritative. A tool error is not permission to bypass those controls.
See TOOLS.md for the public tool inventory and SECURITY.md for security reporting.
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.
- 2d ago First seen · 25 lines · 291 tokens per session scan A 3e507cbdc309
formasty-mcp GEMINI.md is an instructions file published in the GitHub repository QuantumCoderSys/formasty-mcp (0 stars, last pushed 16d ago), licensed MIT. It adds 291 tokens to every session, about $0.0015 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 instructions, from other repositories
9router CLAUDE.md
Claude Code instructions for decolua/9router, covering claude.md, what this is, commands, architecture and request flow (the thing to understand first).
Seo-Promt-Master copilot-instructions.md
Instructions for umutxyp/Seo-Promt-Master: This repository is a prompt-driven SEO audit-and-fix workflow with a runnable live audit tool.
enquire-mcp AGENTS.md
Instructions for oomkapwn/enquire-mcp, covering agents.md, tl;dr, architecture (5-minute orientation), conventions and typescript.
skill.color-expert CLAUDE.md
Claude Code instructions for meodai/skill.color-expert, covering claude.md, project overview, architecture, no build/test/lint and editing guidelines.
Seo-Promt-Master AGENTS.md
Instructions for umutxyp/Seo-Promt-Master, covering agent instructions for this repository and before you open start.md.
health-export-mcp AGENTS.md
Instructions for PhilipAD/health-export-mcp, covering using health-export-mcp with your ai client, claude desktop, cursor, vs code (copilot / continue) and opencode.