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 ai4s-research/ai4s-skills --skill experiment-suitegit clone --depth 1 https://github.com/ai4s-research/ai4s-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/ai4s-research/ai4s-skills/experiment-suite)<a href="https://agentmods.dev/skills/ai4s-research/ai4s-skills/experiment-suite"><img src="https://agentmods.dev/badge/skills/ai4s-research/ai4s-skills/experiment-suite/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/ai4s-research/ai4s-skills/experiment-suite"><img src="https://agentmods.dev/badge/skills/ai4s-research/ai4s-skills/experiment-suite.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 | $0.00048 | $0.02393 |
| Opus 5 | $0.00024 | $0.01196 |
| Sonnet 5 | $0.00010 | $0.00479 |
| Haiku 4.5 | $0.00005 | $0.00239 |
Grade A, and why
experiment-suite 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- experiment-suite — 91% identical, 42 lines differ
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Experiment Suite
Overview
End-to-end experiment package builder. Single stage, full quality from the start. The agent (Claude Code / Cursor / Aider / Codex / …) writes everything directly using its own tools (Write, Bash, WebFetch, …). This skill contains procedure + reference playbooks + figure-example scripts — no Python runtime, no LLM SDK.
The substantive work is decomposed into reference playbooks under references/:
| Reference | Topic |
|---|---|
references/00-incremental-execution.md |
how to do this without losing work: batches, persistence, resume — read first |
references/01-design-depth.md |
what a real experiment design contains (motivation → hypothesis → datasets → baselines → metrics → ablations → budget) |
references/01a-data-contract.md |
runtime dataset binding: source, access route, version, split, and reuse boundary |
references/02-code-quality.md |
code-skeleton standards — runnable model.py, data.py, train.py, evaluate.py |
references/03-results-protocol.md |
results.json schema; measured / simulated / illustrative provenance |
references/04-publication-figures.md |
publication-grade charts, multi-panel layouts, taste rules |
references/04a-figure-contract.md |
figure logic before plotting: conclusion, panel map, reviewer risk |
references/04b-figure-qa.md |
export bundle, editable text, statistics and image-integrity QA |
references/05-report-structure.md |
structured experiment_report.md (problem → design → method → results → analysis → limitations) |
references/06-quality-gate.md |
self-check before delivery |
Also: figure_examples/ — publication-style matplotlib scripts plus a shared style kit the agent can use as starting points.
Read the relevant reference before writing, not after. The full pass does not fit in a single turn — references/00-incremental-execution.md is the only execution mode that completes.
When to Use
- User wants to "design an experiment" for a research question.
- User needs runnable code for a specific task (classification / forecasting / detection / …).
- User wants to compare methods and have a structured report at the end.
- User needs publication-quality figures of experimental results.
What ships with it
17 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.
- figure_examples/FIGURE_CONTRACT_TEMPLATE.md 249 B
- figure_examples/make_fig_02_horizon_sweep.py 1.3 KB runs code
- figure_examples/make_fig_03_heatmap.py 1.6 KB runs code
- figure_examples/make_fig_04_ablation.py 2.1 KB runs code
- figure_examples/README.md 1.3 KB
- figure_examples/requirements.txt 145 B
- figure_examples/style_kit.py 2.3 KB runs code
- references/00-incremental-execution.md 4.5 KB
- references/01-design-depth.md 5.9 KB
- references/01a-data-contract.md 3.0 KB
- references/02-code-quality.md 8.3 KB
- references/03-results-protocol.md 5.9 KB
- references/04-publication-figures.md 8.9 KB
- references/04a-figure-contract.md 1.7 KB
- references/04b-figure-qa.md 2.0 KB
- references/05-report-structure.md 6.6 KB
- references/06-quality-gate.md 6.9 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.
- 12d ago First seen · 159 lines · 48 tokens per session scan A 02d7eedeb9d3
experiment-suite is a skill published in the GitHub repository ai4s-research/ai4s-skills (223 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 2,393 once invoked, about $0.0002 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
publication-figures
Use whenever you generate or review a chart, plot, table, or paper figure in this workspace, including work delegated by paper-writing, literature-survey, and experiment skills. Applies the Open Science publication style, enforces readable final-size layout for figures and tables, and rejects generic diagram-tool…
large-file
Use BEFORE reading any data file that could be large (CSV/TSV, Parquet, HDF5, FITS, NetCDF, NDJSON, genomics FASTQ/FASTA/VCF/BAM, GRIB, ROOT, or big text/simulation logs like VASP OUTCAR). Returns a compact memory pointer — header/schema/shape/sample/key numbers — by introspection and sampling in bounded memory, so…
domain-check
Use whenever you write or run scientific analysis code (physics, earth/geo, biology, chemistry, social science, or bioprocess/fermentation) in this workspace — before executing it and again after generating results. Runs a deterministic domain-correctness gate that catches code which runs but is scientifically wrong…
stats-integrity
Use whenever you run statistical analysis for the social sciences (regression, hypothesis tests, econometrics) or read Stata (.dta) / SPSS (.sav) data in this workspace. Enforces an execute-don't-interpret boundary (surface estimates, don't volunteer causal claims), checks the analysis against a preregistration plan…
remote-compute
Use when the user asks to run, submit, monitor, or cancel a job on a remote machine over SSH — their own GPU/CPU server, a workstation, or a Slurm cluster ("the cluster", a login node, "my 3090 box", "the compute server"). Picks a saved machine, runs the work directly over SSH (or via Slurm when present), tracks it…
modal-run
Use when the user asks to run heavy or GPU work on Modal (the cloud compute platform) — writing a Modal function in the workspace, running it with the user's own modal CLI + token, and bringing results back. Data-to-compute for jobs too big for the laptop, without a Slurm cluster.