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/rishapgandhi/python-skills/agents-mdgit clone --depth 1 https://github.com/rishapgandhi/python-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 | $0.00932 | $0.00932 |
| Opus 5 | $0.00466 | $0.00466 |
| Sonnet 5 | $0.00186 | $0.00186 |
| Haiku 4.5 | $0.00093 | $0.00093 |
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.
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
- Read this file before writing any code.
- Load
skills/common/code-style.mdfor every task. - Load the framework-specific skill (
skills/{framework}/SKILL.md) for the project. - Follow layer discipline: API → Service → Repository → Model.
- Never hardcode secrets — use pydantic-settings.
- All public functions must have docstrings and type annotations.
- Tests mandatory for all business logic (80% coverage minimum).
- 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 |
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.
- yesterday First seen · 85 lines · 932 tokens per session scan A 2b48d5bb35cf
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.
Other instructions, from other repositories
roam-code AGENTS.md
Instructions for Cranot/roam-code, covering agents.md — roam-code development guide, what this project is, documentation hub, where files go (private vs public) and quality discipline (from internal/dogfood/ + agi-in-md).
conforme AGENTS.md
Instructions for maxgfr/conforme, covering project instructions, claude.md, project overview, build & test and architecture.
conforme GEMINI.md
Instructions for maxgfr/conforme, covering claude.md, project overview, build & test, architecture and keeping docs in sync.
conforme copilot-instructions.md
Instructions for maxgfr/conforme, covering claude.md, project overview, build & test, architecture and keeping docs in sync.
agentic-tech-debt CLAUDE.md
Instructions for bcanfield/agentic-tech-debt, covering project rules, adapter parity — duplicated on purpose, what's duplicated (keep in sync), per-adapter deltas (do not sync away) and demo gifs.
agentic-tech-debt AGENTS.md
Instructions for bcanfield/agentic-tech-debt: The agent instructions for this repo live in CLAUDE.md — one source of truth for every coding agent. Read it and follow it as written; it applies to Codex exactly as it does to Claude Code.