Borrowing it
Nothing to install: this file belongs to Asheng008/unifiles-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/Asheng008/unifiles-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/Asheng008/unifiles-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/asheng008/unifiles-mcp/agents-md)<a href="https://agentmods.dev/instructions/asheng008/unifiles-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/asheng008/unifiles-mcp/agents-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/asheng008/unifiles-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/asheng008/unifiles-mcp/agents-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 | $0.01248 | $0.01248 |
| Opus 5 | $0.00624 | $0.00624 |
| Sonnet 5 | $0.00250 | $0.00250 |
| Haiku 4.5 | $0.00125 | $0.00125 |
Grade A, and why
unifiles-mcp AGENTS.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 9d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - Project Context & Directives (v6.0)
SYSTEM NOTICE: This is the highest priority context file for AI Agents (Cursor, Windsurf, Copilot, Sisyphus, etc.). Ensure you read and adhere to these guidelines before executing tasks.
1. Project Overview
- Role: Senior Python Engineer focused on the Model Context Protocol (MCP) ecosystem.
- Tech Stack: Python 3.10+,
mcp(FastMCP SDK),unifiles,pydantic. - Purpose: MCP server for
unifiles(unified file operations library) providing Excel, PDF, Word, and SQLite operations via MCP tools. - Architecture: Strict type annotations, SOLID principles, and clean architecture using FastMCP.
2. Environment & Commands
- Virtual Environment: NEVER use global
pythonorpip. Always use the project's.venvto avoid dependency conflicts.- Linux/Mac:
./.venv/bin/python,./.venv/bin/pip - Windows:
.\.venv\Scripts\python.exe,.\.venv\Scripts\pip.exe
- Linux/Mac:
- Encoding: When handling output in Windows, ensure UTF-8 encoding is used (
chcp 65001).
Build, Lint, and Test Commands
Use the following commands from the project root:
# Code Formatting & Linting (100 line length configured in pyproject.toml)
black src/ tests/ # Format code
ruff check src/ tests/ # Lint code (Auto-fixes: ruff check --fix)
mypy src/ # Strict type checking
# Testing
pytest tests/ -v # Run all tests (see docs/03-TESTING.md)
# Installation
pip install -e ".[dev]" # Install in editable mode with dev dependencies
3. Code Style & FastMCP Guidelines
These rules are defined in .opencode/rules/code_style.md. They are mandatory for all MCP integrations in this repository.
3.1 Core Principles
- FastMCP First: Always use
@mcp.tool(),@mcp.resource(), and@mcp.prompt()frommcp.server.fastmcp.FastMCP. Do not interact with the low-levelServerclass directly. - Type-Driven Schemas: Use Python type hints (
str,int,bool,list) to auto-generate MCP schemas. - Flat Parameters: Prioritize simple, flat parameter lists. Avoid wrapping all inputs in a single Pydantic model or dictionary, which complicates client integration.
- Document Everything: Use docstrings and
Annotated[T, Field(description="...")]. The function's docstring is directly converted to the MCP tool's description field.
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.
- 9d ago First seen · 94 lines · 1,248 tokens per session scan A 49a1deb1630d
unifiles-mcp AGENTS.md is an instructions file published in the GitHub repository Asheng008/unifiles-mcp (0 stars, last pushed 5mo ago), licensed MIT. It adds 1,248 tokens to every session, about $0.0062 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
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.