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-foldx-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-foldx-tool)<a href="https://agentmods.dev/skills/internscience/molclaw/molclaw-foldx-tool"><img src="https://agentmods.dev/badge/skills/internscience/molclaw/molclaw-foldx-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-foldx-tool"><img src="https://agentmods.dev/badge/skills/internscience/molclaw/molclaw-foldx-tool.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
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 | $0.00116 | $0.04209 |
| Opus 5.5 | $0.00046 | $0.01684 |
| Sonnet 5.5 | $0.00023 | $0.00842 |
| Haiku 4.5 | $0.00012 | $0.00421 |
Grade A, and why
molclaw-foldx-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 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 — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FoldX Protein Stability & Mutation Analysis
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.
Critical Prerequisite
MANDATORY: Run
mode=repairpdbon every PDB before any other FoldX mode. FoldX optimizes side-chain rotamers against its own empirical energy function; unrepaired structures produce unreliable energy values. This is independent ofmolclaw-fix-pdb— even pdbfixer-repaired structures need FoldX RepairPDB. The output*_Repair.pdbis the ONLY acceptable input for subsequent FoldX modes.
- For PDB file inputs, it is recommended to preprocess them using
molclaw-fix-pdbbefore FoldX RepairPDB.
When To Use This Skill
| Scenario | Use FoldX | Use other tool instead |
|---|---|---|
| Evaluate protein intrinsic stability (ΔG) | ✅ stability |
— |
| Predict effect of known mutations (ΔΔG) | ✅ buildmodel |
— |
| Protein–protein interface energy (fast, minutes) | ✅ analysecomplex |
MMPBSA (precise, hours) |
| Identify interface hotspot residues | ✅ alascan with chains |
MMPBSA per-residue decomposition (precise) |
| Saturating mutagenesis scan at specific sites | ✅ positionscan |
— |
| Affinity maturation on complex interface | ✅ pssm |
— |
| Per-residue energy decomposition | ✅ sequencedetail |
interaction-visualizer (geometry level) |
| Small-molecule binding free energy | ❌ | Boltz-2, MMPBSA |
| MD trajectory dynamics | ❌ | GROMACS, OpenMM |
| Batch docking pose evaluation | ❌ | EquiScore, ProLIF |
Unified Tool Interface
All 8 modes are accessed through a single tool foldx_tool with a mode parameter. The full parameter set is:
Run FoldX energy evaluation and mutation-scanning workflows for protein stability
or complex-interface screening.
Args:
mode (str): FoldX command mode, REQUIRED. One of: repairpdb, stability,
buildmodel, analysecomplex, alascan, positionscan, pssm, sequencedetail.
pdb_path (str): Input PDB file path, REQUIRED for all modes.
chains (str|None): Complex chain definition, e.g. 'A,B' or 'HL,A'.
REQUIRED for analysecomplex and pssm.
OPTIONAL for alascan (enables complex-mode interface scanning).
Ignored by other modes. Default: None.
positions (str|None): Comma-separated mutation position tokens.
Format: OrigAA(1-letter) + ChainID + ResNum + TargetAA.
REQUIRED for positionscan and pssm. Default: None.
mutant_file (str|None): Path to FoldX-format mutation list file.
REQUIRED for buildmodel. Default: None.
number_of_runs (int): Independent repeats for buildmodel (1-100). Default: 5.
water (str): Water handling: CRYSTAL|PREDICT|NONE|COMPARE. Default: CRYSTAL.
pdb_hydrogens (bool): Read hydrogens from PDB. Default: False.
dry_run (bool): Return planned command without execution. Default: False.
timeout (int): Maximum execution time in seconds. Default: 7200.
Return:
status (str): success | error | partial_success
msg (str): Execution summary or error message
mode (str): Normalized FoldX command mode
output_dir (str|None): Run directory path
foldx_command (str|None): Executed or planned command line
pdb_file (str|None): Input PDB filename in output_dir
key_files (dict): Key output files relative to output_dir
metrics (dict): return_code, generated_file_count, and mode-specific values
(total_energy, mean_ddg, ddg_values, interaction_energy, hotspot_count)
stderr_tail (str, only on error): Last portion of FoldX stderr for diagnostics
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 · -7 lines · +9 tokens per session 73bbc164eebf
- 1mo ago First seen · 337 lines · 107 tokens per session scan A 3db062139a78
molclaw-foldx-tool is a skill published in the GitHub repository InternScience/MolClaw (38 stars, last pushed 1mo ago), licensed MIT. It adds 116 tokens to every session and 4,209 once invoked, about $0.0005 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
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
Performs bounded, local exploratory analysis of explicitly supported scientific files. Supports 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
Builds, reviews, migrates, and plans MATLAB or GNU Octave numerical workflows. Use for arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Builds and analyzes phylogenetic trees using MAFFT multiple sequence alignment, IQ-TREE maximum likelihood with ModelFinder and branch support, and FastTree approximate inference. Uses ETE3 for tree summaries and visualization. Applies to homologous nucleotide or protein sequences, microbial gene trees, protein…
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.
presenting-conference-talks
Generates conference presentation slides (Beamer LaTeX PDF and editable PPTX) from a compiled paper with speaker notes and talk script. Use when preparing oral talks, spotlight presentations, or invited talks for ML and systems conferences.