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 skills add kennethreitz/pytheory-skill --skill composing-with-pytheorygit clone --depth 1 https://github.com/kennethreitz/pytheory-skillWrote 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/skills/kennethreitz/pytheory-skill/composing-with-pytheory)<a href="https://agentmods.dev/skills/kennethreitz/pytheory-skill/composing-with-pytheory"><img src="https://agentmods.dev/badge/skills/kennethreitz/pytheory-skill/composing-with-pytheory/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kennethreitz/pytheory-skill/composing-with-pytheory"><img src="https://agentmods.dev/badge/skills/kennethreitz/pytheory-skill/composing-with-pytheory.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00138 | $0.04618 |
| Opus 5 | $0.00069 | $0.02309 |
| Sonnet 5 | $0.00028 | $0.00924 |
| Haiku 4.5 | $0.00014 | $0.00462 |
Grade A, and why
composing-with-pytheory 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 8d 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.
This is a copy
100% identical to composing-with-pytheory — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Composing with PyTheory
PyTheory turns music theory into runnable Python. You build a Score, add parts
(chords, melodies, basslines) and drums, then render it to audio or MIDI —
every sound is synthesized from math, so there are no samples, plugins, or DAW to
install.
How to work
- Write a short Python script that builds a
Scoreand either plays it or saves it. Don't compose by chaining shell one-liners — a script is clearer, reproducible, and easy to iterate on. - Run it with
uv run python song.pywhen uv is available, otherwisepython3 song.py. - To let the user hear it, call
play_score(score)(speakers) or render to a WAV they can open. To hand off to a DAW, save MIDI.
If PyTheory isn't installed, prefer uv when available: uv pip install pytheory
(or uv add pytheory in a uv project); otherwise pip install pytheory. For live
MIDI input add the extra: uv pip install "pytheory[live]" (or pip install "pytheory[live]"). NumPy/SciPy ship as PyTheory dependencies, so the
scipy.io.wavfile WAV export below needs no extra install.
Core building blocks
from pytheory import Score, Key, Chord, Duration
score = Score("4/4", bpm=120) # time signature + tempo
# A part is a voice with its own synth/instrument and effects.
piano = score.part("piano", instrument="piano", reverb=0.3)
lead = score.part("lead", synth="saw", envelope="pluck", lowpass=4000)
bass = score.part("bass", synth="triangle", lowpass=900)
# Chords from a Key's progression (Roman numerals) or Chord.from_symbol.
for chord in Key("G", "major").progression("I", "V", "vi", "IV"):
piano.add(chord, Duration.WHOLE)
# Melodies are note names + durations (a float = beats, or Duration.*).
lead.add("D5", 1).add("B4", 0.5).add("D5", 0.5).add("G5", 2)
lead.rest(2)
for n in ["G2", "D2", "E2", "C2"]:
bass.add(n, Duration.WHOLE)
part.add(note_or_chord, duration)chains and returns the part.part.rest(duration)inserts silence.Duration.WHOLE / HALF / QUARTER / EIGHTH / SIXTEENTHplus dotted variants (DOTTED_HALF,DOTTED_QUARTER, …), or pass a float in beats (1,0.5,0.25,0.125).Key(tonic, mode).progression("I", "V", "vi", "IV")returnsChords (lowercase numeral = minor, e.g."i","VI").Key(...).chordslists the diatonic chords;Key(...).scalegives the scale tones.Chord.from_symbol("F#m7b5")parses any symbol.- Note names are scientific pitch (
C4= middle C).Tone.from_string("A1")builds an explicit pitch;tone.add(12)/tone.add(-12)shift octaves.
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.
- 8d ago First seen · 330 lines · 138 tokens per session scan A e916e8fa6057
composing-with-pytheory is a skill published in the GitHub repository kennethreitz/pytheory-skill (3 stars, last pushed 2mo ago), licensed MIT. It adds 138 tokens to every session and 4,618 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to composing-with-pytheory, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.