applications AGENTS.md

A set of project instructions for building Python applications and integrations with uv, a tool that manages Python dependencies and commands. It also defines conventions for naming agent tools and testing applications and APIs.

In plain words
What is it for?
It is for developers working on Python-based MCP applications, APIs, integrations, and their tests.
Why use it?
It prevents inconsistent dependency management, command usage, and tool structure across the project.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/universal-mcp/applications/agents-md
Clone the repo
git clone --depth 1 https://github.com/universal-mcp/applications

Made for: Codex, OpenCode.

Per session 9,408 This file is loaded in full into every session.
When invoked 9,408 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.09408 $0.09408
Opus 5 $0.04704 $0.04704
Sonnet 5 $0.01882 $0.01882
Haiku 4.5 $0.00941 $0.00941

Measured yesterday against content hash 3f2653324c36, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

applications 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 yesterday.

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.

AGENTS.md · 1,205 lines

How it starts

The opening of the file, as written. The whole thing — 1,205 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent.md — Python + uv

Purpose

  • This repository uses Python managed by uv for dependency resolution, virtual environments, locking, and execution. Always prefer uv subcommands (add/remove/run/sync/export) over raw pip/venv commands.

Core rules

  • Use uv add to add or upgrade dependencies so that both pyproject.toml and uv.lock stay in sync; do not use pip install directly.
  • Keep runtime dependencies in [project.dependencies] and development-only tools in the dev group via uv add --dev ....
  • Use uv run to execute Python, test, and tooling commands without manually activating a virtual environment.

Project bootstrap

  • New project (scaffold files): uv init
  • First install or clean install: uv sync
  • Run the app: uv run python -m <your_module> or uv run main.py
  • REPL: uv run python
  • Scripts in pyproject: prefer uv run <command> to ensure the correct environment is used

Managing dependencies

  • Add runtime dependency: uv add <name> (e.g., uv add httpx)
  • Add dev dependencies: uv add --dev pytest ruff
  • Pin/upgrade by constraint: uv add "httpx>=0.27" or adjust pyproject.toml and then uv sync
  • Remove dependency: uv remove <name>
  • Export lock for external tooling: uv export --format requirements-txt --output-file requirements.txt

Locking and environments

  • uv run and uv sync will ensure the environment matches pyproject.toml and uv.lock
  • Avoid manual pip install or manual venv activation; let uv manage the environment
  • Commit uv.lock to version control for reproducible installs

pyproject guidance

  • Dependencies live under [project]dependencies = [...]
  • Development-only tooling should go under a dev group (e.g., uv add --dev ruff pytest) for clean separation
  • Keep requires-python current (e.g., >=3.12) to match the team’s baseline

Usage in this repo

  • When adding libraries or changing versions, propose uv add ... changes that update both pyproject.toml and uv.lock, then run uv run pytest -q to validate
  • Prefer minimal diffs, explain the plan, apply changes, and run tests/tooling via uv run
  • If build/test fails, inspect error context, adjust constraints or code, and re-run via uv run

Common commands (copy/paste)

  • Initialize: uv init | Install deps: uv sync
  • Add runtime: uv add <pkg> | Add dev: uv add --dev <pkg>
  • Remove: uv remove <pkg>
  • Run app: uv run python -m <your_module> or uv run main.py
  • Tests: uv run pytest -q
  • Lint/format: uv run ruff check . and/or uv run ruff format .
  • Export: uv export --format requirements-txt --output-file requirements.txt

Of course. Based on your request and the example app.py you provided, here is a new section that you can append to your gemini.md file. This section provides clear guidance on how to write effective tool names and descriptions, using the Perplexity chat function as a concrete example.

The proposed changes will make the function's purpose much clearer, especially its ability to access and cite real-time web information, which is a key feature.


Read the full file on GitHub · 1,205 lines

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. yesterday First seen · 1,205 lines · 9,408 tokens per session scan A 3f2653324c36

Subscribe to this mod's changes

applications AGENTS.md is an instructions file published in the GitHub repository universal-mcp/applications (2 stars, last pushed 4mo ago), licensed MIT. It adds 9,408 tokens to every session, about $0.0470 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.

Related

Other instructions, from other repositories

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

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).

microsoft/vscode · 6,785 tokens

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.

openai/codex · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

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).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens