open-python-skills AGENTS.md

A project guide for a collection of reusable instructions for Python development. It explains the folders, reference files, scripts, and conventions in the project.

In plain words
What is it for?
Working on Python backends, type checking, testing with pytest, Dockerfiles, web scraping, API testing, code quality, observability, notebooks, and data validation.
Why use it?
It helps an agent find the right guidance and follow the project’s established way of working instead of guessing where things belong.

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/jiatastic/open-python-skills/agents-md
Clone the repo
git clone --depth 1 https://github.com/jiatastic/open-python-skills

Made for: Codex, OpenCode.

Per session 348 This file is loaded in full into every session.
When invoked 348 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 $0.00348 $0.00348
Opus 5 $0.00174 $0.00174
Sonnet 5 $0.00070 $0.00070
Haiku 4.5 $0.00035 $0.00035

Measured 2d ago against content hash 3a7997037fb7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

open-python-skills 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 2d 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.

AGENTS.md · 42 lines

What it actually says

PROJECT KNOWLEDGE BASE

OVERVIEW

A collection of AI-ready skill bundles for Python development.

STRUCTURE

open_python_skills/
├── python-backend/      # FastAPI, SQLAlchemy, Redis patterns
├── commit-message/      # Git commit message generation
├── excalidraw-ai/       # Diagram generation
├── ty-skills/           # Python type checking with ty
├── unit-testing/        # pytest patterns
├── docker-builder/      # Dockerfile generation
├── web-scraping/        # Scraping patterns
├── api-testing/         # API testing with schemathesis
├── linting/             # Ruff linting
├── formatting/          # Code formatting
├── observability/       # OpenTelemetry + Logfire
├── error-handling/      # Error handling patterns
├── marimo-notebook/     # Marimo notebooks
└── pydantic/            # Pydantic validation

WHERE TO LOOK

Task Location
Skill catalog open_python_skills/*/SKILL.md
Reference docs open_python_skills/*/references/*.md
Data files open_python_skills/*/data/*.json
Scripts open_python_skills/*/scripts/*.py

CONVENTIONS

  • Each skill has a SKILL.md with front-matter metadata
  • Reference docs live in references/ subdirectory
  • JSON data lives in data/ subdirectory
  • Excalidraw libraries live in assets/ subdirectory
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. 2d ago First seen · 42 lines · 348 tokens per session scan A 3a7997037fb7

Subscribe to this mod's changes

open-python-skills AGENTS.md is an instructions file published in the GitHub repository jiatastic/open-python-skills (9 stars, last pushed 7mo ago), licensed MIT. It adds 348 tokens to every session, about $0.0017 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.