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.
Borrowing it
Nothing to install: this file belongs to skyllwt/AutoSci. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/skyllwt/AutoSci/main/.claude/skills/exp-pilot-run/SKILL.mdgit clone --depth 1 https://github.com/skyllwt/AutoSciWrote 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/skyllwt/autosci/exp-pilot-run)<a href="https://agentmods.dev/skills/skyllwt/autosci/exp-pilot-run"><img src="https://agentmods.dev/badge/skills/skyllwt/autosci/exp-pilot-run/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/skyllwt/autosci/exp-pilot-run"><img src="https://agentmods.dev/badge/skills/skyllwt/autosci/exp-pilot-run.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 | $0.00054 | $0.03584 |
| Opus 5.5 | $0.00022 | $0.01434 |
| Sonnet 5.5 | $0.00011 | $0.00717 |
| Haiku 4.5 | $0.00005 | $0.00358 |
Grade A, and why
exp-pilot-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 2mo 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 — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/exp-pilot-run
Execute a pilot experiment described by a Pilot Spec YAML file. Reads the spec from
experiments/pilot/{slug}.yaml, writes pilot code, runs the experiment(Confirm with the user before operation and require the applicant to conduct manual inspection), and returns raw results to the caller. No matter which operating mode is adopted, before the experimental code is ready for deployment and operation, confirmation shall be obtained from users. Users need to manually check relevant information including codes and experimental configurations(Such as dataset paths, interface parameter selection, API configuration and so on). The operation can only be launched after confirmation. Otherwise, revisions shall be made repeatedly until users approve the execution. Supports local (direct GPU) and remote (SSH deployment viatools/remote.py) modes. Does NOT modify any wiki pages. Does NOT judge pass/fail — results are evaluated by/exp-pilot-eval.
Inputs
idea-slug: slug used to locateexperiments/pilot/{slug}.yaml--env local|remote(optional, defaultlocal): deployment environmentlocal: run directly on local GPUremote: deploy to remote machine via SSH (requiresconfig/server.yaml)
Outputs
- Pilot code:
experiments/pilot/code/{slug}/(train.py, config.yaml, run.sh, requirements.txt) - Pilot results:
experiments/pilot/code/{slug}/results/seed_{N}.json - Pilot log:
experiments/pilot/code/{slug}/pilot.log - PILOT_REPORT (printed to terminal) — results table, run details, anomalies
- Returns raw results and key metrics to caller
- NO wiki page modifications
Wiki Interaction
Reads
experiments/pilot/{slug}.yaml— Pilot Spec (all configuration) If the Pilot Spec for the selected idea does not exist at the corresponding position, remind the user and create it following the steps for creating a Pilot Spec in /ideate Phase 5.wiki/papers/*.md— related papers' method descriptions (implementation reference)
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.
- 2mo ago First seen · 271 lines · 54 tokens per session scan A 15ed2587759f
exp-pilot-run is a skill published in the GitHub repository skyllwt/AutoSci (1,706 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 3,584 once invoked, about $0.0002 per session on Opus 5.5. 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.
exp-pilot-run compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| exp-pilot-runskyllwt/AutoSci | Skill | 1.7k | 1mo ago | MIT | A | 54 | Claude Code |
| instrument-data-to-allotropeanthropics/knowledge-work-plugins | Skill | 35k | 2d ago | Apache-2.0 | A | 123 | Claude Code |
| exploratory-data-analysisK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 83 | Claude Code |
| matlabK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 44 | Claude Code |
| phylogeneticsK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 71 | Claude Code, Codex |
| research-engineerdavila7/claude-code-templates | Skill | 33k | yesterday | MIT | A | 43 | Claude Code, Codex |
| mapping-to-snomedmaziyarpanahi/openmed | Skill | 5.8k | yesterday | Apache-2.0 | A | 205 | Claude Code |