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/songshgeo/python-project-template/claude-mdgit clone --depth 1 https://github.com/SongshGeo/Python-Project-TemplateWhat 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 | $0.01101 | $0.01101 |
| Opus 5 | $0.00550 | $0.00550 |
| Sonnet 5 | $0.00220 | $0.00220 |
| Haiku 4.5 | $0.00110 | $0.00110 |
Grade A, and why
Python-Project-Template 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 3d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude Code (and any AI agent) working in this repository. This is
the authoritative source for coding standards and the skill/workflow index.
The Cursor rules in .cursor/rules/cursorrules.mdc are kept in sync with this
file; if the two ever diverge, this file wins.
This is a modern, bilingual (English + 中文) Python project template. It is managed exclusively with uv (no poetry).
Read the memory bank first
Before any non-trivial work, read the shared memory bank in memory-bank/:
architecture.md— high-level structure, module boundaries, key flows.model-design.md— domain/data model: core entities, relationships, invariants.tech-stack.md— chosen tools and the rationale behind them.progress.md— current progress, open questions, next steps.
These files are shared by both Cursor and Claude Code. Keep them up to date:
when architecture, data shapes, or tooling change, update the relevant file;
append short, actionable notes to progress.md and prune stale ones. Per-task
implementation plans live in memory-bank/plans/.
Coding standards
- Typing: every function and class gets full type annotations, including
explicit return types (
Nonewhere appropriate). - Docstrings: Google-style docstrings on all public functions/classes (PEP 257). Update docstrings when behavior changes.
- Comments: preserve existing comments; match the surrounding style.
- Error handling: avoid bare/broad
try…exceptthat silently swallows exceptions — let failures surface or handle them explicitly with logging. - Style: Black (88 cols), isort (
--profile black), Ruff (lint + format). Docstring coverage is gated by interrogate (--fail-under=80). - Dependencies: manage with
uvonly (uv add,uv sync). Runtime deps go in[project.dependencies]; dev/docs in[project.optional-dependencies].
Testing
- Use pytest only (never
unittest). Tests live undertests/. - Fully annotate tests and give them docstrings. Add
__init__.pywhen creating new packages undertests/orsrc/<package>. - When you need pytest fixtures, import them under
TYPE_CHECKING:CaptureFixture,FixtureRequest,LogCaptureFixture,MonkeyPatch(_pytest.*),MockerFixture(pytest_mock.plugin). - Coverage target: ≥80% overall, aim for 100% on core logic.
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.
- 3d ago First seen · 96 lines · 1,101 tokens per session scan A 8cab037305ed
Python-Project-Template CLAUDE.md is an instructions file published in the GitHub repository SongshGeo/Python-Project-Template (8 stars, last pushed 2mo ago), licensed MIT. It adds 1,101 tokens to every session, about $0.0055 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
AutoProver CLAUDE.md
Claude Code instructions for Certora/AutoProver, covering repository conventions for coding agents, pre-validating a commit, python and do not use from future import annotations.
apm python.instructions.md
Python development guidelines.
pysm AGENTS.md
Instructions for galsci/pysm, covering repository guidelines, project overview, project structure & key files, quick start commands and setup environment.
django-starter-template AGENTS.md
Instructions for wilfredinni/django-starter-template, covering agents.md, commands, lint & typecheck, architecture and testing.
foundry-local python-cffi-pointer-types.instructions.md
Use when working on the Python SDK's native bindings (cffi), especially when defining new Item subclasses, working with flItemQueue, or extending Request/Session methods that pass native handles.
llm-ide-rules pytest-tests.instructions.md
Instructions for iloveitaly/llm-ide-rules, covering pytest tests, example test and file structure.