Borrowing it
Nothing to install: this file belongs to conversiontools/gemini-extension. 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/conversiontools/gemini-extension/main/GEMINI.mdgit clone --depth 1 https://github.com/conversiontools/gemini-extensionWrote 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/conversiontools/gemini-extension/gemini-md)<a href="https://agentmods.dev/instructions/conversiontools/gemini-extension/gemini-md"><img src="https://agentmods.dev/badge/instructions/conversiontools/gemini-extension/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/conversiontools/gemini-extension/gemini-md"><img src="https://agentmods.dev/badge/instructions/conversiontools/gemini-extension/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 | $0.00990 | $0.00990 |
| Opus 5.5 | $0.00396 | $0.00396 |
| Sonnet 5.5 | $0.00198 | $0.00198 |
| Haiku 4.5 | $0.00099 | $0.00099 |
Grade A, and why
gemini-extension 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
3. The response includes a `download_url`. Download the result with `curl -sL "<download_url>" -o <output>`. How it starts
The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conversion Tools
conversiontools is a file-conversion integration provided by this extension via the hosted Conversion Tools MCP server (https://mcp.conversiontools.io/mcp). It converts files between 140+ formats: documents, data (JSON, CSV, XML, YAML, Parquet), images, audio, video, e-books, OCR, subtitles, AI-powered data extraction, text-to-speech, and speech-to-text. It can also build a custom converter from a plain-language description when no standard converter fits (see "Build a custom converter" below).
It is NOT a Maven/npm/build plugin and has nothing to do with any local project file. Do not search the web for it and do not inspect project source to convert a file - use the MCP tools below.
If the tools are not available
The conversiontools tools only appear after the MCP server is authenticated. If you do not see tools like convert_file / list_converters, tell the user to run:
/mcp auth conversiontools
This opens a browser for a one-time OAuth login. After that, the tools load automatically.
How to convert a file
- Pick the converter. Call
find_converterwith the input and output formats (e.g.{ "input_format": "xml", "output_format": "csv" }). It returns the converter type, for exampleconvert.xml_to_csv. You can also pass thatconverterexplicitly toconvert_file. - Provide the file content. The server is remote and cannot read local paths, so:
- Files up to 5 MB: read the file yourself and pass its bytes base64-encoded as
file_content, along withinput_pathandoutput_path. Encode the file in-process rather than shelling out - agent sandboxes (Gemini CLI, for one) block PowerShell and$(...)base64 one-liners as "command substitution", so a shell command like[Convert]::ToBase64String(...)will fail. If you must shell out, use a clean encoder such asbase64 -w0 file(no line wrapping); nevercertutil -encode, which wraps the output in-----BEGIN CERTIFICATE-----headers and corrupts it. - Files over 5 MB: call
request_upload_url, PUT the file to the returned URL, then callconvert_filewith the returnedfile_idinstead offile_content.
- Files up to 5 MB: read the file yourself and pass its bytes base64-encoded as
- The response includes a
download_url. Download the result withcurl -sL "<download_url>" -o <output>.
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 · 48 lines · 990 tokens per session scan A 1ae1d9fc1c6d
gemini-extension GEMINI.md is an instructions file published in the GitHub repository conversiontools/gemini-extension (3 stars, last pushed 5d ago), licensed MIT. It adds 990 tokens to every session, about $0.0040 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.