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 InternScience/MolClaw --skill molclaw-chroma-toolkitgit clone --depth 1 https://github.com/InternScience/MolClawWrote 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/internscience/molclaw/molclaw-chroma-toolkit)<a href="https://agentmods.dev/skills/internscience/molclaw/molclaw-chroma-toolkit"><img src="https://agentmods.dev/badge/skills/internscience/molclaw/molclaw-chroma-toolkit/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/internscience/molclaw/molclaw-chroma-toolkit"><img src="https://agentmods.dev/badge/skills/internscience/molclaw/molclaw-chroma-toolkit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00099 | $0.01877 |
| Opus 5.5 | $0.00040 | $0.00751 |
| Sonnet 5.5 | $0.00020 | $0.00375 |
| Haiku 4.5 | $0.00010 | $0.00188 |
Grade A, and why
molclaw-chroma-toolkit 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 1mo 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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chroma Protein Generation Toolkit
Invocation
Use the exact tool name and parameter schema exposed by the current harness. Tool names in SDK examples below are raw MCP names, not model-facing aliases. Local files must be uploaded with molclaw-file-transfer before a server tool can use them. Repair PDB inputs first when the workflow requires it.
Usage
1. Monomer Protein Generation
The description of tool chroma_monomer.
Generates a de novo single-chain protein candidate for exploratory protein design workflows.
Args:
length (int): Number of residues in the monomer chain. Default: 100.
steps (int): Diffusion sampling step count. Default: 500.
device (str): Chroma execution device string. Default: 'cuda:0'.
fmt (str): Output structure format, one of {'cif', 'pdb'}. Default: 'cif'.
api_key (str|None): Optional Chroma API key for model access.
dry_run (bool): If True, validate parameters and prepare output paths without model sampling. Default: False.
Return:
status (str): 'success' or 'error'.
msg (str): Human-readable execution summary.
tool_name (str): Tool identifier 'chroma_monomer'.
output_dir (str): Run-specific output directory under tool_result/chroma_toolkit_result.
output_file (str): Target output structure file path.
length (int): Effective residue length used in generation.
steps (int): Effective sampling steps used in generation.
device (str): Effective execution device.
format (str): Effective output format.
How to use tool chroma_monomer :
response = await client.session.call_tool(
"chroma_monomer",
arguments={
"length": 150,
"steps": 500,
"device": "cuda:0",
"fmt": "cif",
"dry_run": False
}
)
result = client.parse_result(response)
output_file = result["output_file"]
Example parameter sets
# 1) Main mode
{
"length": 150,
"steps": 500,
"device": "cuda:0",
"fmt": "cif",
"dry_run": False
}
# 2) Variant mode
{
"length": 100,
"steps": 50,
"fmt": "cif",
"dry_run": True
}
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.
- 1mo ago Changed · -1 lines · +55 tokens per session 25524ff28c39
- 1mo ago First seen · 230 lines · 44 tokens per session scan A 3756d59f6318
molclaw-chroma-toolkit is a skill published in the GitHub repository InternScience/MolClaw (38 stars, last pushed 1mo ago), licensed MIT. It adds 99 tokens to every session and 1,877 once invoked, about $0.0004 per session on Opus 5.5. 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
torchdrug
Builds and troubleshoots TorchDrug 0.2.1 workflows for molecular graphs, property prediction, self-supervised pretraining, molecule generation, retrosynthesis, protein representation learning, and knowledge graph reasoning. Use when code imports torchdrug or needs its datasets, models, tasks, or Engine.
arboreto
Infers candidate gene regulatory networks from bulk or single-cell expression data using AertsLab Arboreto GRNBoost2 and GENIE3. Use for transcription factor-target association ranking, compatible Dask execution, sparse expression inputs, and network stability checks.
deepspot-m
Generates transcriptome-wide virtual spatial transcriptomics from H&E histology with DeepSpot-M. Used for predicted log1p-CPM expression from 224x224 tiles at about 20x, querying the released protein-coding gene panel by symbol, and whole-slide prediction after resolution-aware tiling with histolab.
pyhealth
Builds and validates PyHealth clinical machine-learning pipelines for EHR, signals, imaging, and medical codes. Use for PyHealth dataset loading, MIMIC-III/IV, eICU or OMOP prediction tasks, patient-level evaluation, mortality/readmission/length-of-stay modeling, medication recommendation, sleep staging, Trainer…
nemo-mbridge-perf-expert-parallel-overlap
Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlapmoeexpertparallelcomm, delaywgradcompute, and flex dispatcher backends such as DeepEP and HybridEP.
ml-training-recipes
Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning…