ARIS is a collection of Markdown-based skills that define a workflow for autonomous machine-learning research, including idea discovery, experiment automation, and review loops. Researchers and AI coding agents use it across tools such as Claude Code, Codex, Cursor, and OpenClaw without depending on a single framework. The catalogue entries are ARIS workflow skills and agents.
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 wanshuiyin/Auto-claude-code-research-in-sleep --skill lean-formalizegit clone --depth 1 https://github.com/wanshuiyin/Auto-claude-code-research-in-sleepWrote 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/wanshuiyin/auto-claude-code-research-in-sleep/lean-formalize)<a href="https://agentmods.dev/skills/wanshuiyin/auto-claude-code-research-in-sleep/lean-formalize"><img src="https://agentmods.dev/badge/skills/wanshuiyin/auto-claude-code-research-in-sleep/lean-formalize/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/wanshuiyin/auto-claude-code-research-in-sleep/lean-formalize"><img src="https://agentmods.dev/badge/skills/wanshuiyin/auto-claude-code-research-in-sleep/lean-formalize.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 | $0.00081 | $0.04200 |
| Opus 5.5 | $0.00032 | $0.01680 |
| Sonnet 5.5 | $0.00016 | $0.00840 |
| Haiku 4.5 | $0.00008 | $0.00420 |
Grade A, and why
lean-formalize 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 today.
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 — 364 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lean Formalize
Turn the user's mathematical statement into a checked Lean theorem with its meaning preserved. A compiled conditional lemma is progress; completion concerns the original statement and the trust basis actually used.
When to use Lean
Use this skill when the user requests Lean, when continuing an existing Lean
proof, or when formal verification addresses a concrete uncertainty in a central
claim—for example, a long dependency chain, a delicate reduction, or coverage of
a finite classification. State the obligation it will help resolve and proceed
within the authorized task. Difficulty alone is not a reason to formalize.
Ordinary derivations and short proofs can stay in formula-derivation or
proof-writer; do not make Lean a prerequisite for every mathematical result.
Respect the user's chosen proof method and the scale of the requested work.
Core workflow
Original statement and Lean definitions
→ A: cross-family adversarial statement alignment
→ Proof obligations, representations, and lemma interfaces
→ Lean implementation ↔ B: adversarial review of key arguments and connections
→ Actual inputs connected; original theorem assembled
→ Executed type, definition, and transitive-axiom audit
→ C: cross-family adversarial review of the final exported result
→ Reproducible delivery and research-state update
For substantial new proof projects, A/B/C are part of the workflow. For a continuation, reuse completed checks on unchanged claims and revisit affected ones. Small routine formalizations need checks proportional to the actual claim; an explicit user request for cross-family review still applies to them.
Use the authorized reviewer families available in the current host. If the user specifies both Grok and Gemini, obtain and record both; a same-family agent or another provider does not silently satisfy either request. Unavailability leaves that checkpoint pending while independent proof work continues. A checked theorem and a fully completed requested review workflow are separate deliverables.
What ships with it
3 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.
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.
- today First seen · 364 lines · 81 tokens per session scan A 14f18d5314b7
lean-formalize is a skill published in the GitHub repository wanshuiyin/Auto-claude-code-research-in-sleep (17,059 stars, last pushed yesterday), licensed MIT. It adds 81 tokens to every session and 4,200 once invoked, about $0.0003 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 2026-10-07.
Other skills, from other repositories
talk-builder
Turn a paper (or several, a thesis, a body of work) into an academic talk — outline, per-slide content, speaker notes, opening hook, single take-home message, backup slides for Q&A, rehearsal plan. Adapts to talk length (3-min lightning through 90-min defense), audience (specialists / general field /…
remote-compute-ssh
Evaluate and use SSH Remote Compute before choosing where to run GPU, high-memory, parallel, batch, model-inference, bioinformatics, or other long-running scientific work; supports short remote commands and asynchronous jobs with automatic harvest and analysis.
figure-style
Publication-grade correctness and legibility rules for final-deliverable scientific figures, not exploratory plots. Use for a figure that will ship in a report, paper, export, or kept artifact. Covers data fidelity, label economy, color threading, chart choice, layout, and render-then-verify QA without imposing a…
alphafold2
Predict protein structure for monomers and multimers with AlphaFold2 via the ColabFold runner (Mirdita et al. 2022, github.com/sokrypton/ColabFold; AlphaFold2 Jumper et al. 2021). Reach for this skill to fold a sequence or complex with the AF2/AF2-Multimer evoformer, to validate designed sequences by self-consistency…
boltz
Structure prediction for protein, nucleic-acid, and small-molecule complexes with Boltz-2 (Passaro & Wohlwend et al. 2025, github.com/jwohlwend/boltz). Reach for this skill to validate designed binders against a target, to co-fold a protein with a SMILES or CCD ligand, or to get an open-source AlphaFold3 alternative…
scgpt
Embed and annotate single-cell expression data with scGPT, a foundation model for single-cell biology. Use this skill when: (1) Producing cell embeddings from an AnnData for clustering/integration, (2) Zero-shot or fine-tuned cell-type annotation, (3) Gene-level representation for perturbation/GRN tasks. For…