exp-run

exp-run is a skill for Claude Code from skyllwt/AutoSci. It costs 35 tokens per session (4,807 once invoked), scanned A, original, MIT.

A workflow for running planned experiments from preparation through deployment, monitoring, and result collection. It supports separate modes for starting an experiment, checking a running one, or completing a short run end to end.

In plain words
What is it for?
Use it to launch experiments described in a project wiki, monitor long-running jobs, and collect results when they finish.
Why use it?
It keeps experiment execution organized and requires the user to review code and settings before anything is deployed.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions CLAUDE.md; mentions Claude Code.

Not installable on its own: it runs a file from its repository that does not travel with it. Clone the repository, or install whatever ships that file. The line is python3 tools/research_wiki.py set-meta \.

About the project

AutoSci is an AI research platform organized around a wiki, with an agent that supports stages of scientific work such as reading, experimentation, writing, and retaining knowledge across projects. It is for people building or using AI-assisted research workflows, with Claude Code, Codex, and OpenCode adaptations available. The catalogue add-ons extend those agent-specific workflows.

skyllwt/AutoSci · 1,660 stars · on GitHub

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code.

Wrote 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.

agentmods badge for exp-run

README.md
[![agentmods](https://agentmods.dev/badge/skills/skyllwt/autosci/exp-run.svg)](https://agentmods.dev/skills/skyllwt/autosci/exp-run)
Your own site
<a href="https://agentmods.dev/skills/skyllwt/autosci/exp-run"><img src="https://agentmods.dev/badge/skills/skyllwt/autosci/exp-run.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,807 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00035 $0.04807
Opus 5 $0.00017 $0.02403
Sonnet 5 $0.00007 $0.00961
Haiku 4.5 $0.00003 $0.00481

Measured 6d ago against content hash 528b94ed5496, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

exp-run 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 6d 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.

.claude/skills/exp-run/SKILL.md · 419 lines

How it starts

The opening of the file, as written. The whole thing — 419 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/exp-run

Execute an experiment that has been planned in wiki/experiments/. No matter which operation mode it is, before preparing the experimental codes and deploying them for operation, confirmation shall be obtained from users. Users need to manually check relevant information such as codes and experimental configurations(Dataset paths, interface parameter selection, API configuration, etc.). The operation can only be launched after confirmation; otherwise, revisions shall be made repeatedly until users approve the execution. Three run modes for different scenarios:

  • Default (deploy): Phase 1-2 only — deploy and return immediately. Best for experiments that take hours or days.
  • --collect: Phase 3-4 only — check whether a deployed experiment has finished; collect results if so (--check is an alias).
  • --full: All four phases end-to-end. Best for short local experiments that finish in minutes.

Recommended flow: /exp-run <slug> to deploy → /exp-status to monitor → /exp-run <slug> --collect to collect.

Inputs

  • experiment: slug from wiki/experiments/
    • deploy mode: status must be planned
    • --collect mode: status must be running
    • --full mode: status must be planned
  • --review (optional): enable Review LLM code review for experiment code in Phase 1 (valid in deploy / full mode)
  • --collect (optional): collect mode — check if the experiment has finished and collect results; --check is an alias
  • --full (optional): full mode — execute all 4 phases (best for quick local experiments)
  • --env local|remote (optional, default local): deployment environment
    • local: run directly on local GPU
    • remote: deploy to remote machine via SSH (requires config/server.yaml)

Outputs

  • deploy mode:
    • Experiment code: experiments/code/{slug}/ (generated in Phase 1)
    • wiki/experiments/{slug}.md — status: planned → running
    • DEPLOY_REPORT (printed to terminal) — deployment confirmation, session info, next steps
    • wiki/log.md — appended deploy log
  • collect mode (experiment has finished):
    • wiki/experiments/{slug}.md — status: running → completed; outcome/key_result/date_completed filled in
    • RUN_REPORT (printed to terminal) — result summary, metrics comparison, next step suggestions
    • wiki/log.md — appended collect log
  • collect mode (experiment still running):
    • Progress report printed to terminal only; wiki is not modified
  • full mode: all outputs from both deploy and collect

Read the full file on GitHub · 419 lines

Changes

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.

  1. 6d ago First seen · 419 lines · 35 tokens per session scan A 528b94ed5496

Subscribe to this mod's changes

exp-run is a skill published in the GitHub repository skyllwt/AutoSci (1,660 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 4,807 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.

Related

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…

anthropics/knowledge-work-plugins · 123 tokens

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.

K-Dense-AI/scientific-agent-skills · 42 tokens

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…

K-Dense-AI/scientific-agent-skills · 83 tokens

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.

K-Dense-AI/scientific-agent-skills · 68 tokens

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.

davila7/claude-code-templates · 43 tokens

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…

maziyarpanahi/openmed · 205 tokens