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/softnanolab/bagel/bagel-script-buildernpx skills add softnanolab/bagel --skill bagel-script-buildergit clone --depth 1 https://github.com/softnanolab/bagelWrote 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/softnanolab/bagel/bagel-script-builder)<a href="https://agentmods.dev/skills/softnanolab/bagel/bagel-script-builder"><img src="https://agentmods.dev/badge/skills/softnanolab/bagel/bagel-script-builder.svg" alt="Measured on agentmods" 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 | $0.00322 | $0.03568 |
| Opus 5 | $0.00161 | $0.01784 |
| Sonnet 5 | $0.00064 | $0.00714 |
| Haiku 4.5 | $0.00032 | $0.00357 |
Grade A, and why
bagel-script-builder 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 5d 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 — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Building BAGEL protein-design scripts, interactively
BAGEL (pip name biobagel, imported as import bagel as bg) frames protein design as
minimizing an energy landscape: you describe what a good design looks like as a sum of
weighted energy terms, then a Monte-Carlo minimizer mutates the mutable residues to lower that
energy. The scripts are the documentation — there is no config/YAML layer.
This skill is not a one-shot code generator. It runs an interactive workflow so the user ends up with correct, fully-specified, well-explained, reviewable scripts. Work through the phases below in order. Do not skip the interview: silently guessing the parts of a design the user left unspecified is the main failure mode this skill exists to prevent.
The workflow at a glance
- Understand & draft — read the natural-language goal, write a first-pass draft script.
- Interview to close gaps — walk the user through the draft and ask about everything the description left unclear, until every State, Chain, and EnergyTerm (and each term's inputs) is explicitly pinned down.
- Write the design script — verbose, heavily commented, saved to disk for review.
- Smoke test — generate a minimal test script; run it on Modal if credentials are available, and report exactly what worked or failed.
- Single run or sweep? — ask whether this is one run or a repeat over some "difference".
- Execution harness — if a sweep, generate the launcher (SLURM / PBS / Modal-parallel / serial-background), one output folder per run, runnable via a single command.
Always save every script to disk (never only paste into chat) so the user can review, edit,
and re-run them. Default to a bagel_designs/<short-project-name>/ directory in the working
directory unless the user names a location; put the design script, smoke test, and any sweep
harness there together.
Every file this skill generates must begin with an agent-disclaimer comment, so it is always
clear the file was written with AI assistance and should be reviewed before use. Use this block
verbatim at the very top of every .py and .sh file you create (adjust the comment character
for shell scripts; fill in today's date if you know it):
What ships with it
9 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.
- assets/pbs_job.sh 1.4 KB runs code
- assets/slurm_job.sh 1.5 KB runs code
- assets/submit_cluster.py 4.2 KB runs code
- assets/sweep_config.py 5.1 KB runs code
- assets/sweep_runner.py 7.7 KB runs code
- references/api-reference.md 13 KB
- references/clarification-checklist.md 4.8 KB
- references/execution-harness.md 6.4 KB
- references/patterns.md 11 KB
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.
- 5d ago First seen · 238 lines · 322 tokens per session scan A a4d158ad54b3
bagel-script-builder is a skill published in the GitHub repository softnanolab/bagel (143 stars, last pushed 23d ago), licensed MIT. It adds 322 tokens to every session and 3,568 once invoked, about $0.0016 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…