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 Ling-MD/md-agent-skills --skill pymol-academic-figuresgit clone --depth 1 https://github.com/Ling-MD/md-agent-skillsWrote 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/ling-md/md-agent-skills/pymol-academic-figures)<a href="https://agentmods.dev/skills/ling-md/md-agent-skills/pymol-academic-figures"><img src="https://agentmods.dev/badge/skills/ling-md/md-agent-skills/pymol-academic-figures/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/ling-md/md-agent-skills/pymol-academic-figures"><img src="https://agentmods.dev/badge/skills/ling-md/md-agent-skills/pymol-academic-figures.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 | $0.00082 | $0.01076 |
| Opus 5 | $0.00041 | $0.00538 |
| Sonnet 5 | $0.00016 | $0.00215 |
| Haiku 4.5 | $0.00008 | $0.00108 |
Grade A, and why
pymol-academic-figures 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 12d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PyMOL Academic Figures
Use PyMOL to make clean, reproducible molecular figures for papers, posters, talks, and reports. Prefer scripted .pml generation over manual GUI steps so figures can be regenerated after structure or style changes.
This skill is adapted for Codex from the PyMOL figure workflow in claudemol, with local command-line rendering added for this machine.
Local Environment
Use these commands directly:
pymol -cq figure.pml
claudemol --help
Known local paths:
C:\Users\dell\Downloads\PyMOL-3.1.6.1_appveyor2641-Win64-portable-py310\PyMOL\Scripts\pymol.exe
C:\Users\dell\Downloads\PyMOL-3.1.6.1_appveyor2641-Win64-portable-py310\PyMOL\pymol.cmd
C:\Users\dell\Downloads\PyMOL-3.1.6.1_appveyor2641-Win64-portable-py310\PyMOL\claudemol.cmd
For headless batch rendering, prefer:
python C:\Users\dell\.codex\skills\pymol-academic-figures\scripts\run_pymol_render.py --pml figure.pml --output figure.png
Workflow
- Clarify the scientific message: binding site, conformational change, alignment, interaction network, surface property, mutation, epitope, or MD snapshot.
- Identify the input: PDB ID, local
.pdb/.cif, trajectory-derived snapshot, aligned structures, ligand/cofactor, or user-provided session. - Generate a
.pmlscript with deterministic object names, selections, colors, camera, labels, image dimensions, and output path. - Render headlessly with
run_pymol_render.pyorpymol -cq. - Inspect the resulting PNG. Fix clipping, crowded labels, hidden ligand, low contrast, bad orientation, or excessive visual complexity.
Figure Standards
Default publication settings:
bg_color white
set ray_opaque_background, off
set antialias, 2
set ray_trace_mode, 1
set ray_shadows, off
set ambient, 0.35
set direct, 0.65
set spec_reflect, 0.15
set cartoon_fancy_helices, on
set cartoon_smooth_loops, on
set depth_cue, off
set orthoscopic, on
Use 2400 x 1800 for most single-panel figures. Use 3000 x 2400 or higher when labels or surfaces need extra room. Export transparent backgrounds only when the downstream layout needs it.
What ships with it
3 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.
- 12d ago First seen · 102 lines · 82 tokens per session scan A 591f52afb128
pymol-academic-figures is a skill published in the GitHub repository Ling-MD/md-agent-skills (4 stars, last pushed 3mo ago), licensed MIT. It adds 82 tokens to every session and 1,076 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
ase-atomistic
Atomic Simulation Environment (ASE) for atomistic simulations: structure building, geometry optimization, NEB, molecular dynamics, and trajectory analysis.
mdanalysis-trajectory
Analyze molecular dynamics trajectories with MDAnalysis — RMSD, RMSF, hydrogen bonds, contact maps, and protein-ligand distances.
md-analysis
This skill covers quantitative post-processing of atomistic molecular dynamics trajectories: loading and preprocessing trajectories from LAMMPS, GROMACS, or ASE; computing structural observables (RDF, coordination numbers, angular distributions, bond orientational order, common-neighbor analysis, centrosymmetry…
md-force-fields
This skill covers selection, validation, and deployment of interatomic force fields for molecular dynamics: the physical basis and transferability limits of every major functional form (EAM, MEAM, Tersoff, Stillinger-Weber, Buckingham, COMB, ReaxFF, AMBER, CHARMM, OPLS, GROMOS, and ML potentials); parameter-file…
reactive-md
This skill covers reactive molecular dynamics (reactive MD) using LAMMPS with the ReaxFF and COMB force fields: force-field selection and parameter provenance, charge equilibration (QEq) setup and diagnostics, timestep and thermostat selection for reactive systems, thermal protocols for reaction sampling, reaction…
coarse-grained-md
This skill covers coarse-grained (CG) molecular dynamics: mapping atomistic structures to CG bead representations, parameterizing CG force fields (Martini 3, iterative Boltzmann inversion, force matching), running CG simulations in GROMACS and LAMMPS, backmapping CG configurations to atomistic resolution, and…