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 uchicago-dsi/ai-sci-skills --skill research-code-parsimonygit clone --depth 1 https://github.com/uchicago-dsi/ai-sci-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/uchicago-dsi/ai-sci-skills/research-code-parsimony)<a href="https://agentmods.dev/skills/uchicago-dsi/ai-sci-skills/research-code-parsimony"><img src="https://agentmods.dev/badge/skills/uchicago-dsi/ai-sci-skills/research-code-parsimony/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/uchicago-dsi/ai-sci-skills/research-code-parsimony"><img src="https://agentmods.dev/badge/skills/uchicago-dsi/ai-sci-skills/research-code-parsimony.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 | $0.00059 | $0.00980 |
| Opus 5 | $0.00030 | $0.00490 |
| Sonnet 5 | $0.00012 | $0.00196 |
| Haiku 4.5 | $0.00006 | $0.00098 |
Grade A, and why
research-code-parsimony 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 4d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Code Parsimony
Establish The Contract And The Owner First
Before adding code, be able to state:
- the behavior or scientific contract being requested, including what must stay reproducible;
- the module, function, script, or config that already owns this behavior, and which callers actually exercise it;
- whether a maintained dependency or a native language/library capability already provides it.
Search before creating an owner. If none fits a genuinely new capability, create one clear owner rather than forcing unrelated behavior into an existing module.
Reuse Before You Add
- Extend an understood existing owner instead of introducing a parallel one.
- Prefer a maintained dependency when it reduces ownership burden while meeting the scientific and operational contract. Check the standard library and present dependencies first.
- Parsimony means less code to own — not fewest files, shortest diff, or clever one-liners. Readable, explicit code beats a compressed version.
- Never satisfy the request by solving a smaller or easier scientific problem than the one asked for.
Express Cohesive Families As Directories
Prefer a meaningful package hierarchy over a flat directory of long,
repeated-prefix filenames. When several modules belong to one scientific or
contract family, let the directory carry that context and give the modules
short role names: for example,
training/concentration_field/diffusion/runtime.py rather than
training/concentration_field_diffusion_runtime.py. A separate
training/physics_field/direct_inverse/ can own its own data, objective, and QC
modules; genuinely shared training infrastructure stays at the shared level.
Group by cohesive ownership, not chronology, and add depth only when it makes
navigation and responsibilities clearer. Do not create speculative package
trees or duplicate a family merely to achieve symmetry.
Apply this preference when choosing a new owner's home. Existing flat families can move in a bounded, authorized pass coordinated with their current owners; this preference does not authorize reorganizing active work during another task. Leave queued/running execution checkouts and immutable run artifacts untouched. Move live imports, entrypoints, config references, and hashed execution declarations together, updating valid source pins according to local policy. Validate the affected execution paths and remove old module routes without compatibility aliases. Completed runs retain their producing layout through their pinned commits, not duplicate source at HEAD.
What ships with it
1 file 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.
- 4d ago First seen · 83 lines · 59 tokens per session scan A b5c139a9a53c
research-code-parsimony is a skill published in the GitHub repository uchicago-dsi/ai-sci-skills (17 stars, last pushed today), licensed MIT. It adds 59 tokens to every session and 980 once invoked, about $0.0003 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 2026-09-05.
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…