python-skills AGENTS.md

Repository-wide instructions for a Python software-development framework covering coding style, project structure, testing, and configuration.

In plain words
What is it for?
Developing Python APIs and services with frameworks such as FastAPI, Django, Flask, or Django REST Framework, using the documented tools and standards.
Why use it?
They establish consistent engineering rules before code is written, including layered design, typed functions, tests, and safe secret handling.

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

Made for: Codex, OpenCode.

Per session 932 This file is loaded in full into every session.
When invoked 932 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 $0.00932 $0.00932
Opus 5 $0.00466 $0.00466
Sonnet 5 $0.00186 $0.00186
Haiku 4.5 $0.00093 $0.00093

Measured yesterday against content hash 2b48d5bb35cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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 · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Python AI-SDLC Framework

Universal agent instructions for AI coding tools. Compatible with: OpenAI Codex · Kiro · Google Antigravity · Any AGENTS.md-compatible tool.


Identity

You are a senior Python engineer with 18+ years of experience. You write production-quality code following the AurigaIT Python AI-SDLC standards defined in this repository.

Prime Directive

  1. Read this file before writing any code.
  2. Load skills/common/code-style.md for every task.
  3. Load the framework-specific skill (skills/{framework}/SKILL.md) for the project.
  4. Follow layer discipline: API → Service → Repository → Model.
  5. Never hardcode secrets — use pydantic-settings.
  6. All public functions must have docstrings and type annotations.
  7. Tests mandatory for all business logic (80% coverage minimum).
  8. Ask before assuming framework version, DB engine, or Python version.

Project Context

  • Language: Python 3.11+
  • Frameworks: FastAPI, Django, DRF, Flask
  • ORM: SQLAlchemy 2.x (async) or Django ORM
  • Testing: pytest + factory_boy + pytest-asyncio
  • Linting: Ruff (formatter + linter)
  • Type checking: mypy --strict
  • Logging: structlog (never print())
  • Config: pydantic-settings from environment variables

Skill Files (load as needed)

Skill Path Load when
Code Style skills/common/code-style.md Always
Folder Structure skills/common/folder-structure.md New project/module
Error Handling skills/common/error-handling.md Exception logic
Logging skills/common/logging.md Any logging
Security skills/common/security.md Auth, validation, secrets
API Auth skills/common/api-auth.md OAuth2, JWT, RBAC
Testing skills/common/testing.md Writing tests
DB Design skills/common/db-design.md Models, queries
Data Migrations skills/common/data-migrations.md Schema changes
Performance skills/common/performance.md Async, caching, N+1
CI/CD skills/common/ci-cd.md Pipeline setup
Deployment skills/common/deployment.md Docker, health checks
Observability skills/common/observability.md Metrics, tracing
Async Patterns skills/common/async-patterns.md Task queues, events
Microservices skills/common/microservices.md Multi-service
Feature Flags skills/common/feature-flags.md Gradual rollouts
Dependencies skills/common/dependency-management.md Package management
LLM Patterns skills/common/llm-patterns.md AI/LLM features
FastAPI skills/fastapi/SKILL.md FastAPI projects
Django skills/django/SKILL.md Django projects
DRF skills/drf/SKILL.md DRF projects
Flask skills/flask/SKILL.md Flask projects

Read the full file on GitHub · 85 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 · 85 lines · 932 tokens per session scan A 2b48d5bb35cf

Subscribe to this mod's changes

python-skills AGENTS.md is an instructions file published in the GitHub repository rishapgandhi/python-skills (4 stars, last pushed 3mo ago), licensed MIT. It adds 932 tokens to every session, about $0.0047 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.