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 skills/k-dense-ai/scientific-agent-skills/cirqnpx skills add K-Dense-AI/scientific-agent-skills --skill cirqgit clone --depth 1 https://github.com/K-Dense-AI/scientific-agent-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 | $0.00067 | $0.02791 |
| Opus 5 | $0.00034 | $0.01396 |
| Sonnet 5 | $0.00013 | $0.00558 |
| Haiku 4.5 | $0.00007 | $0.00279 |
Grade A, and why
cirq 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 yesterday.
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 — 371 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cirq - Quantum Computing with Python
Cirq is Google Quantum AI's open-source framework for designing, simulating, and running quantum circuits on quantum computers and simulators.
When to Use This Skill
Use this skill when:
- Building, simulating, or optimizing NISQ circuits in Python
- Running jobs on Google Quantum AI processors (via
cirq-google) or partner backends (IonQ, Azure Quantum, AQT, Pasqal) - Modeling noise, compiling to hardware gatesets, or designing characterization experiments
- Using parameter sweeps, transformers, or the ReCirq experiment patterns
For IBM hardware use qiskit; for quantum ML with autodiff use pennylane; for physics simulations use qutip.
Installation
Requires Python 3.11+. Current stable release: 1.6.1 (August 2025). Vendor packages share the same version number.
uv pip install "cirq==1.6.1"
For hardware integration (pin matching versions for reproducibility):
# Google Quantum Engine (requires approved GCP project access)
uv pip install "cirq-google==1.6.1"
# IonQ
uv pip install "cirq-ionq==1.6.1"
# AQT (Alpine Quantum Technologies)
uv pip install "cirq-aqt==1.6.1"
# Pasqal
uv pip install "cirq-pasqal==1.6.1"
# Azure Quantum (IonQ, Honeywell/Quantinuum backends)
uv pip install "azure-quantum[cirq]"
For latest features during development, omit version pins; for production or hardware runs, pin all packages to the same Cirq release.
Quick Start
Basic Circuit
import cirq
import numpy as np
# Create qubits
q0, q1 = cirq.LineQubit.range(2)
# Build circuit
circuit = cirq.Circuit(
cirq.H(q0), # Hadamard on q0
cirq.CNOT(q0, q1), # CNOT with q0 control, q1 target
cirq.measure(q0, q1, key='result')
)
print(circuit)
# Simulate
simulator = cirq.Simulator()
result = simulator.run(circuit, repetitions=1000)
# Display results
print(result.histogram(key='result'))
Parameterized Circuit
import sympy
# Define symbolic parameter
theta = sympy.Symbol('theta')
# Create parameterized circuit
circuit = cirq.Circuit(
cirq.ry(theta)(q0),
cirq.measure(q0, key='m')
)
# Sweep over parameter values
sweep = cirq.Linspace('theta', start=0, stop=2*np.pi, length=20)
results = simulator.run_sweep(circuit, params=sweep, repetitions=1000)
# Process results
for params, result in zip(sweep, results):
theta_val = params['theta']
counts = result.histogram(key='m')
print(f"θ={theta_val:.2f}: {counts}")
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 371 lines · 67 tokens per session scan A 80df5ee951c8
cirq is a skill published in the GitHub repository K-Dense-AI/scientific-agent-skills (40,390 stars, last pushed yesterday), licensed MIT. It adds 67 tokens to every session and 2,791 once invoked, about $0.0003 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 skills, from other repositories
discovery-toolbox
A routed repertoire of 90 scientific thinking operators for biological research agents - visual reasoning, detectability and information budgets, search reframing, causal identification, competing explanations, observation and selection processes, pipeline artifact diagnosis, effort allocation, and confirmation…
alphafold-pocket-evaluator
Parses AlphaFold2 PDB files, computes per-residue pLDDT confidence scores, and evaluates Solvent Accessible Surface Area (SASA) of active site pockets.
pydeseq2-bulk-rna
Automated negative binomial differential gene expression analysis, log2 fold-change calculation, p-value adjustment (FDR), and Volcano plot generation.
scanpy-sc-analyzer
Autonomous single-cell RNA-seq quality control filtering, Harmony batch-effect correction, Leiden clustering, UMAP visualization, and marker gene annotation.
card-amr-profiler
Scans bacterial genome assemblies against CARD (Comprehensive Antibiotic Resistance Database) and ResFinder to map drug-class resistance heatmaps.
diffdock-virtual-screener
Runs DiffDock generative diffusion models for blind protein-ligand docking against AlphaFold structures and ranks candidates by confidence scores.