PyTheory is a Python toolkit for exploring music theory and composing music, with immediate audio playback and visual representations such as guitar tabs and chord diagrams. Musicians and programmers use it to create arrangements across multiple musical systems, instruments, rhythms, and effects. The catalogue add-ons provide agent guidance for working with the project.
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/kennethreitz/pytheory/claude-mdgit clone --depth 1 https://github.com/kennethreitz/pytheoryWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/kennethreitz/pytheory/claude-md)<a href="https://agentmods.dev/instructions/kennethreitz/pytheory/claude-md"><img src="https://agentmods.dev/badge/instructions/kennethreitz/pytheory/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00348 | $0.00348 |
| Opus 5 | $0.00174 | $0.00174 |
| Sonnet 5 | $0.00070 | $0.00070 |
| Haiku 4.5 | $0.00035 | $0.00035 |
Grade A, and why
pytheory 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 5d 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.
What it actually says
Claude Code Instructions
Release Process
When releasing to PyPI, always do all three:
- Tag the commit:
git tag v0.X.Y - Push the tag:
git push origin --tags - Create a GitHub release:
gh release create v0.X.Y --title "v0.X.Y: Short description" --notes "Release notes" --latest
Don't forget to update CHANGELOG.md before the release commit.
Version Bumping
pyproject.tomlandpytheory/__init__.pymust match- Run
uv lockafter changing the version - Patch releases (0.X.Y) for bug fixes and small additions
- Minor releases (0.X.0) for new features
Testing
uv run python -m pytest tests/ -x -q --tb=short -m "not slow"
Publishing
Preferred — uses the existing ~/.pypirc credentials, no token in the chat:
uv build && uvx twine upload dist/pytheory-0.X.Y*
(uv publish does NOT read ~/.pypirc; only use uv publish --token <token>
as a fallback if .pypirc isn't available.)
Music Preferences
- Detune: keep at 8-15, don't go above 25
- Humanize: 0.2 is the sweet spot for melodic parts
- Drum humanize: 0.15 default is good
- No swing unless specifically asked
- Sine and triangle are underrated — use them more
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.
- 5d ago First seen · 44 lines · 348 tokens per session scan A 651bef361de0
pytheory CLAUDE.md is an instructions file published in the GitHub repository kennethreitz/pytheory (1,640 stars, last pushed 1mo ago), licensed MIT. It adds 348 tokens to every session, about $0.0017 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 2026-08-30.
Other instructions, from other repositories
libthumbor AGENTS.md
AGENTS.md instructions for thumbor/libthumbor, covering agents.md, dev environment setup, running tests, code style and project structure.
maui performance-hotpaths.instructions.md
Instructions for dotnet/maui, covering performance-critical path rules, hot paths in maui, allocation avoidance, caching and invalidation and collection iteration.
apm python.instructions.md
Python development guidelines.
technocore-chat AGENTS.md
AGENTS.md instructions for flop-labs/technocore-chat: CI runs exactly these — run them before pushing.
solo copilot-instructions.md
Copilot instructions for hiero-ledger/solo, covering github copilot instructions for hiero-ledger/solo and highest-frequency rules.
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.