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-proteinmpnn-toolgit 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-proteinmpnn-tool)<a href="https://agentmods.dev/skills/internscience/molclaw/molclaw-proteinmpnn-tool"><img src="https://agentmods.dev/badge/skills/internscience/molclaw/molclaw-proteinmpnn-tool/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-proteinmpnn-tool"><img src="https://agentmods.dev/badge/skills/internscience/molclaw/molclaw-proteinmpnn-tool.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 | $0.00026 | $0.00945 |
| Opus 5 | $0.00013 | $0.00473 |
| Sonnet 5 | $0.00005 | $0.00189 |
| Haiku 4.5 | $0.00003 | $0.00094 |
Grade A, and why
molclaw-proteinmpnn-tool 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 9d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ProteinMPNN Sequence Design
Note:
- Local files are not directly accessible by the server. Please upload them to the server using
molclaw-file-transferbefore execution. - For PDB file inputs, it is recommended to preprocess them using
molclaw-pdbfixerbefore execution. - Please refer to skill
molclaw-scp-serverto complete tool invocation.
Usage
1. Protein Sequence Design and Scoring
The description of tool proteinmpnn_tool.
Run ProteinMPNN sequence design or scoring from protein structures with optional chain constraints and amino-acid controls.
Args:
pdb_input (str): Input PDB file path or a directory containing multiple PDB files.
model_name (str): Model name in {v_48_002, v_48_010, v_48_020, v_48_030} (default: "v_48_020").
use_soluble (bool): Use soluble-protein model weights (default: False).
ca_only (bool): Run CA-only model mode (default: False).
num_seq (int): Number of sequences generated per target (default: 8).
sampling_temp (str): Sampling temperature string; supports multiple values separated by spaces (default: "0.1").
chains_to_design (str): Chain IDs to redesign, e.g. "A" or "A C" (default: "").
fixed_positions (str): Residue position lists for chain constraints (default: "").
specify_non_fixed (bool): Interpret listed positions as designable positions instead of fixed positions (default: False).
homooligomer (bool): Enable tied-position design for homooligomers (default: False).
omit_aas (str): Globally omitted amino acids (default: "X").
bias_aa (str): Amino-acid bias JSON string (default: "").
score_only (bool): Run scoring-only mode instead of sequence generation (default: False).
path_to_fasta (str): FASTA path used in scoring mode (default: "").
save_probs (bool): Save probability matrices (default: False).
seed (int): Random seed (default: 0).
skip_check (bool): Skip dependency checks in source pipeline (default: False).
dry_run (bool): Validate inputs and create run directory without executing the pipeline (default: False).
Return:
status (str): "success", "error", or "partial_success".
msg (str): Human-readable execution summary.
output_dir (str): Unique run directory under tool_result/proteinmpnn_tool_result.
results_dir (str): Result directory path under output_dir/results.
model_name (str): Effective model name used in this run.
num_seq (int): Effective number of sequences used in this run.
sampling_temp (str): Effective sampling temperature used in this run.
score_only (bool): Effective scoring mode flag.
dry_run (bool): Effective dry-run flag.
output_files (dict): Produced output paths such as seqs/scores/probs directories.
metrics (dict): Summary metrics, including sequence/score/prob file counts when available.
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.
- 9d ago First seen · 95 lines · 26 tokens per session scan A 36d62a0ee55f
molclaw-proteinmpnn-tool is a skill published in the GitHub repository InternScience/MolClaw (33 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 945 once invoked, about $0.0001 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
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…