Borrowing it
Nothing to install: this file belongs to pwntato/skillz_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/pwntato/skillz_mcp/main/GEMINI.mdgit clone --depth 1 https://github.com/pwntato/skillz_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/pwntato/skillz_mcp/gemini-md)<a href="https://agentmods.dev/instructions/pwntato/skillz_mcp/gemini-md"><img src="https://agentmods.dev/badge/instructions/pwntato/skillz_mcp/gemini-md/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/instructions/pwntato/skillz_mcp/gemini-md"><img src="https://agentmods.dev/badge/instructions/pwntato/skillz_mcp/gemini-md.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 | $0.01324 | $0.01324 |
| Opus 5.5 | $0.00530 | $0.00530 |
| Sonnet 5.5 | $0.00265 | $0.00265 |
| Haiku 4.5 | $0.00132 | $0.00132 |
Grade A, and why
skillz_mcp GEMINI.md scanned grade A 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 2mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl http://localhost:8000/skills How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GEMINI.md
Project Overview
This project is a FastAPI server that serves as the MCP (Mission Control Plane). It is built with Python 3.11 and runs in a Docker container managed by Docker Compose. The application code is designed for hot-reloading. It also includes a "skills" feature that allows for progressive loading of tools and functionality for an LLM.
Building and Running
To build and run the server, use the following command:
docker compose up -d
The server will be available at http://localhost:8000.
Development Conventions
- The main application code is located in the
appdirectory. - Python dependencies are managed in the
requirements.txtfile. - The
skillzdirectory is mounted into the container at/skillzand can be used for storing and accessing data. - The
tmpdirectory is available for generating or copying files locally during development or agent operations. Its contents are git-ignored.
Skills
The skillz directory contains a collection of skills that can be progressively loaded and used by an LLM. Each skill is a directory that contains a SKILL.md file with YAML front matter for the name and description of the skill. The SKILL.md file can then reference other files within the skill's directory.
To create a new skill:
- Create a new directory in the
skillzdirectory. - Create a
SKILL.mdfile in the new directory with YAML front matter fornameanddescription. - Add any other files for the skill in the same directory and reference them in the
SKILL.mdfile.
- New skill folders added to the
skillzdirectory will be ignored by Git, except forskillz/sample_skill/.
API Endpoints
The following endpoints are available:
GET /: Redirects to the FastAPI documentation.GET /skills: Returns aninstructionfield explaining the purpose of skills for LLMs, along with a list of all available skills.GET /skills/{skill_id}: Returns aninstructionfield explaining the purpose of skills for LLMs, along with the content of theSKILL.mdfile for the specified skill.GET /skills/{skill_id}/{file_path}: Returns aninstructionfield explaining the purpose of skills for LLMs, along with the content of a specific file for the specified skill.GET /skills/{skill_id}/files: Returns aninstructionfield explaining the purpose of skills for LLMs, along with a list of all files for the specified skill.
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.
- 2mo ago First seen · 100 lines · 1,324 tokens per session scan A d6b295b261a2
skillz_mcp GEMINI.md is an instructions file published in the GitHub repository pwntato/skillz_mcp (0 stars, last pushed 1y ago), licensed MIT. It adds 1,324 tokens to every session, about $0.0053 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.
skillz_mcp GEMINI.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| skillz_mcp GEMINI.mdpwntato/skillz_mcp | Instructions file | 0 | 1y ago | MIT | A | 1,324 | Gemini CLI |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |