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/conversiontools/agent-skills/gemini-mdgit clone --depth 1 https://github.com/conversiontools/agent-skillsWhat 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 | $0.00519 | $0.00519 |
| Opus 5 | $0.00260 | $0.00260 |
| Sonnet 5 | $0.00104 | $0.00104 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
agent-skills 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 26 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conversion Tools Gemini Extension
This extension converts files between 140+ formats using Conversion Tools, via the hosted MCP server (https://mcp.conversiontools.io/mcp). It can also build a custom converter from a plain-language description when no standard converter fits.
Authentication
On first use you will be prompted to authenticate via OAuth - a browser window opens to log in to your Conversion Tools account. Free accounts get 100 conversions per month (10 per day); paid plans are at https://conversiontools.io/pricing.
Usage
Ask Gemini to convert a file and it will pick the right converter automatically:
- "Convert data.json to Excel"
- "Extract the table from invoice.pdf to CSV"
- "Transcribe meeting.mp3 to text"
When no standard converter fits, ask Gemini to build one: "Build a converter that turns this CSV into JSON, one object per invoice with a nested line_items array." The studio_* tools create the converter, run it, and return the result - it persists in your account to continue on the web. Because it persists, you can reuse it later on a new file (studio_list_converters to find it, studio_attach_file to point it at the new file, then run) - no rebuild.
To pull named fields out of documents (invoices, receipts, purchase orders, statements, forms, scans), the parse_* tools drive Parse: "Extract invoice number, date, total and line items from invoice.pdf." Submission is asynchronous by design - parse_extract returns an extraction id, then parse_extraction_status is polled until the extraction is completed or failed, and parse_export turns the result into CSV or XLSX. See https://parse.conversiontools.io/docs.
For files up to 5 MB the agent passes the file base64-encoded as file_content - it reads the file directly and encodes it in-process, rather than relying on a shell base64 one-liner (some agent sandboxes block those as "command substitution"). For files over 5 MB it uses request_upload_url first, then convert_file with the returned file_id.
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.
- 3d ago First seen · 26 lines · 519 tokens per session scan A c1cc2a3c66e9
agent-skills GEMINI.md is an instructions file published in the GitHub repository conversiontools/agent-skills (7 stars, last pushed 1mo ago), licensed MIT. It adds 519 tokens to every session, about $0.0026 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
contentforge AGENTS.md
Instructions for indranilbanerjee/contentforge, covering contentforge — agent context, what this plugin is, how to use it as an agent, canonical entry points and files in this repo.
penalista-italia CLAUDE.md
Claude Code instructions for Synthos-Logic/penalista-italia, covering kit penalista italiano — istruzioni operative, dati dello studio, regole operative fondamentali, struttura del kit and le 9 skill.
mcp-pandoc AGENTS.md
Instructions for vivekVells/mcp-pandoc, covering agents.md, what this is, where things are, deeper context and commands.
excel-mcp-server CLAUDE.md
Instructions for TangentDomain/excel-mcp-server, covering excel mcp server, 技术栈, 目录结构, mcp 工具 → python api 映射 and sql 核心原则.
agentic-resume-builder CLAUDE.md
Claude Code instructions for WtotdeD/agentic-resume-builder, covering agentic-resume-builder development guidelines, what this repo is, active technologies, package manager and validation.
agent-plugins-skills AGENTS.md
Instructions for richfrem/agent-plugins-skills, covering agents.md, 1. think before coding, 2. simplicity first, 3. surgical changes and 4. goal-driven execution.