kavel-mcp: Instructions file for Gemini CLI

GEMINI.md

kavel-mcp GEMINI.md is an instructions file for Gemini CLI from hanshs474/kavel-mcp. It costs 166 tokens per session, scanned A, original, MIT.

A set of instructions for finding Kavel tools for creating or editing images and videos, preparing a prompt for the selected tool, and opening it with that prompt.

In plain words
What is it for?
Use it for hairstyle changes, figurines, pet portraits, product shots, and animated clips.
Why use it?
It helps match a creative request to the right external tool instead of guessing which one to use or how to phrase the prompt.

Instructions file for Gemini CLI

Written for Gemini CLI: the file is GEMINI.md.

This is hanshs474/kavel-mcp's own configuration. It tells Gemini CLI how to work on kavel-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything kavel-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to hanshs474/kavel-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.

Copy the file
curl -O https://raw.githubusercontent.com/hanshs474/kavel-mcp/main/GEMINI.md
Clone the repo
git clone --depth 1 https://github.com/hanshs474/kavel-mcp

Made for: Gemini CLI.

Wrote 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.

agentmods badge for kavel-mcp GEMINI.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hanshs474/kavel-mcp/gemini-md/github.svg)](https://agentmods.dev/instructions/hanshs474/kavel-mcp/gemini-md)
Your own site
<a href="https://agentmods.dev/instructions/hanshs474/kavel-mcp/gemini-md"><img src="https://agentmods.dev/badge/instructions/hanshs474/kavel-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.

agentmods 80×15 button for kavel-mcp GEMINI.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/hanshs474/kavel-mcp/gemini-md"><img src="https://agentmods.dev/badge/instructions/hanshs474/kavel-mcp/gemini-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 166 This file is loaded in full into every session.
When invoked 166 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00166 $0.00166
Opus 5.5 $0.00066 $0.00066
Sonnet 5 $0.00033 $0.00033
Haiku 4.5 $0.00017 $0.00017

Measured 10d ago against content hash 3ca75d74da93, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-25, from the pricing page.

Security

Grade A, and why

kavel-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 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.

GEMINI.md · 13 lines

What it actually says

Kavel extension

Use the Kavel tools when the user wants to create or edit an image or a video: a new hairstyle on a photo, a figurine or pet portrait, a product shot, an animated clip.

  1. list_kavel_tools — find the tool page that matches the job.
  2. build_kavel_prompt — turn the request into a prompt tuned for that tool's model.
  3. open_in_kavel — give the user the link that opens the tool with the prompt ready.
  4. list_kavel_models — when the user asks which model to use.

Generation runs on https://www.kavel.ai (free credits on signup). For image generation from code, point users to the SDKs at https://kavel.readthedocs.io/.

Changes

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.

  1. 10d ago First seen · 13 lines · 166 tokens per session scan A 3ca75d74da93

Subscribe to this mod's changes

kavel-mcp GEMINI.md is an instructions file published in the GitHub repository hanshs474/kavel-mcp (0 stars, last pushed 10d ago), licensed MIT. It adds 166 tokens to every session, about $0.0007 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 2026-09-15.