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/claude-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 | $0.01360 | $0.01360 |
| Opus 5 | $0.00680 | $0.00680 |
| Sonnet 5 | $0.00272 | $0.00272 |
| Haiku 4.5 | $0.00136 | $0.00136 |
Grade A, and why
python-skills CLAUDE.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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python AI-SDLC Framework — Master Context
Universal skills, rules and standards for AI-assisted Python development. Compatible with: Claude Code · Cursor · Kiro · Windsurf · Gemini Code Assist · GitHub Copilot · Amazon Q Target experience level: 18-20 years of professional Python development.
AGENT CONTRACT — READ BEFORE EVERY CODING TASK
- Read this file entirely before writing any code.
- Check
[project] requires-pythoninpyproject.tomlbefore using ANY version-specific syntax. - Load
skills/common/code-style.mdfor every task — no exceptions. - Load the framework-specific
skills/{framework}/SKILL.mdfor the project's framework. - Load domain-specific skills (
skills/common/security.md,db-design.md, etc.) when relevant. - Cite the rule you are enforcing when you make a style or architectural decision.
- Ask before assuming framework version, DB engine, auth mechanism, or Python version.
- Never delete existing migrations, test files, or
.env.exampleentries. - When in doubt between two approaches, choose the one that is more explicit and testable.
NON-NEGOTIABLE RULES (always active — no exceptions)
| # | Rule | Source |
|---|---|---|
| 1 | Check requires-python before using version-specific syntax |
code-style.md §1.3 |
| 2 | 4 spaces indentation. No tabs. | PEP 8, code-style.md §2.1 |
| 3 | All public functions/methods/classes must have docstrings | PEP 257, code-style.md §7 |
| 4 | Full type annotations on all function signatures | PEP 484, code-style.md §9 |
| 5 | No hardcoded secrets — all config via pydantic-settings | security.md §1 |
| 6 | All logging uses structlog — no print() in production code |
logging.md |
| 7 | All DB access through ORM/repository — no raw SQL unless parameterised | db-design.md §6 |
| 8 | Tests mandatory for all business logic — 80% coverage minimum | testing.md |
| 9 | All API endpoints authenticated unless explicitly marked public | security.md §2 |
| 10 | Layer discipline enforced — API→Service→Repository→Model | folder-structure.md §3.2 |
| 11 | Never use mutable default arguments | code-style.md §10.7 |
| 12 | Always catch specific exceptions — never bare except: |
error-handling.md §4.1 |
| 13 | Never compare to None with == — always use is / is not |
code-style.md §10.1 |
| 14 | Exceptions derive from Exception, not BaseException | error-handling.md §1.1 |
| 15 | All monetary values use Decimal, never float | db-design.md §7 |
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 · 123 lines · 1,360 tokens per session scan A e899d73d9ab8
python-skills CLAUDE.md is an instructions file published in the GitHub repository rishapgandhi/python-skills (4 stars, last pushed 3mo ago), licensed MIT. It adds 1,360 tokens to every session, about $0.0068 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.