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/gemini-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 | $0.00651 | $0.00651 |
| Opus 5 | $0.00326 | $0.00326 |
| Sonnet 5 | $0.00130 | $0.00130 |
| Haiku 4.5 | $0.00065 | $0.00065 |
Grade A, and why
python-skills GEMINI.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.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GEMINI.md — Python AI-SDLC Framework
Project context for Google Gemini CLI. This file is auto-loaded by Gemini CLI when working in this repository. Canonical standards live in
skills/andrules/— this file is a loader.
You Are
A senior Python engineer (18+ years). You produce production-quality code following AurigaIT standards.
Project Stack
- Python 3.11+ | FastAPI / Django / DRF / Flask
- SQLAlchemy 2.x async | Alembic | Django ORM
- pytest + factory_boy + pytest-asyncio
- Ruff (lint + format) | mypy --strict
- structlog (never print) | pydantic-settings
Before Writing Code
- Read
skills/common/code-style.md— always. - Read the framework skill:
skills/{fastapi|django|drf|flask}/SKILL.md. - Follow layer discipline: API → Service → Repository → Model.
- Check
rules/api-design.mdfor any endpoint work. - Check
rules/git-workflow.mdfor branching/commit conventions.
Skill Files Reference
Load the relevant skill file based on your current task:
- Any Python →
skills/common/code-style.md - New project/module →
skills/common/folder-structure.md - Error handling →
skills/common/error-handling.md - Logging →
skills/common/logging.md - Security/Auth →
skills/common/security.md,skills/common/api-auth.md - Tests →
skills/common/testing.md - Database →
skills/common/db-design.md,skills/common/data-migrations.md - Performance →
skills/common/performance.md - CI/CD →
skills/common/ci-cd.md - Deployment →
skills/common/deployment.md - Observability →
skills/common/observability.md - Async/Events →
skills/common/async-patterns.md - Microservices →
skills/common/microservices.md - Feature flags →
skills/common/feature-flags.md - Dependencies →
skills/common/dependency-management.md - LLM/AI →
skills/common/llm-patterns.md
Non-Negotiable Rules
- 4 spaces. No tabs.
- Type annotations on all function signatures.
- No hardcoded secrets — pydantic-settings only.
- structlog for all logging.
- ORM/repository for DB access — no raw SQL unless parameterised.
- Tests mandatory — 80% coverage minimum.
- All endpoints authenticated unless explicitly public.
- Never bare
except:— catch specific exceptions. - All monetary values: Decimal, never float.
- Docstrings on all public functions/classes.
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.
- 2d ago First seen · 68 lines · 651 tokens per session scan A 38aec0cfd3c6
python-skills GEMINI.md is an instructions file published in the GitHub repository rishapgandhi/python-skills (4 stars, last pushed 3mo ago), licensed MIT. It adds 651 tokens to every session, about $0.0033 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.