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
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/wanshuiyin/Auto-claude-code-research-in-sleepnpx agentmods add skills/wanshuiyin/auto-claude-code-research-in-sleep/grant-proposalWrote 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/grant-proposal)<a href="https://agentmods.dev/skills/wanshuiyin/auto-claude-code-research-in-sleep/grant-proposal"><img src="https://agentmods.dev/badge/skills/wanshuiyin/auto-claude-code-research-in-sleep/grant-proposal/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/grant-proposal"><img src="https://agentmods.dev/badge/skills/wanshuiyin/auto-claude-code-research-in-sleep/grant-proposal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk fail
- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 632 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Rogue Agent · line 632 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00131 | $0.08640 |
| Opus 5 | $0.00066 | $0.04320 |
| Sonnet 5 | $0.00026 | $0.01728 |
| Haiku 4.5 | $0.00013 | $0.00864 |
Grade A, and why
grant-proposal 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- grant-proposal — 86% identical, 79 lines differ
How it starts
The opening of the file, as written. The whole thing — 699 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grant Proposal: From Research Ideas to Fundable Application
Draft a grant proposal based on: $ARGUMENTS
Overview
This skill turns validated research ideas into a structured, reviewer-ready grant proposal. It chains sub-skills into a grant-specific pipeline:
/research-lit → /novelty-check → [structure design] → [draft] → /research-review → [revise] → GRANT_PROPOSAL.md
(survey) (verify gap) (aims + matrix) (prose) (panel review) (fix) (done!)
This is a parallel branch, not part of the linear Workflow 1→1.5→2→3 pipeline. After /idea-discovery produces validated ideas, the user can either:
- Go to
/experiment-bridge→/auto-review-loop→/paper-writing(implement & publish) - Go to
/grant-proposal(write funding application first, then implement after funding)
┌→ /experiment-bridge → /auto-review-loop → /paper-writing (publish track)
/idea-discovery ────┤
└→ /grant-proposal → [get funded] → /experiment-bridge → ... (funding track)
Grant proposals argue for future work (feasibility + potential), not completed work (results + claims). This skill handles the unique requirements of grant writing: narrative arc design, reviewer-facing structure, budget justification, timeline planning, and agency-specific formatting.
Constants
- GRANT_TYPE =
KAKENHI— Default grant type. Supported:KAKENHI,NSF,NSFC,ERC,DFG,SNSF,ARC,NWO,GENERIC. Override via argument (e.g.,/grant-proposal "topic — NSF"). - GRANT_SUBTYPE =
auto— Sub-type within the grant agency. Examples: KAKENHIStart-up/Wakate/Kiban-B; NSFCYouth/Excellent-Youth/Distinguished/Overseas/Key; NSFCAREER/CRII/Standard. Auto-detected from argument or defaults to the most common sub-type. - REVIEWER_MODEL =
gpt-6-astra— Model used via Codex MCP for proposal review. Must be an OpenAI model (e.g.,gpt-6-astra,o3,gpt-4o). - OUTPUT_FORMAT =
markdown— Output format. Supported:markdown,latex. LaTeX uses grant-specific templates when available. - MAX_REVIEW_ROUNDS = 2 — Maximum external review-revise cycles before finalizing.
- OUTPUT_DIR =
grant-proposal/— Directory for generated proposal files. - LANGUAGE =
auto— Output language. Auto-detected from grant type: KAKENHI→Japanese, NSF→English, NSFC→Chinese, ERC→English, DFG→English (or German), SNSF→English, ARC→English, NWO→English. Override explicitly if needed. - AUTO_PROCEED = false — At each checkpoint, always wait for explicit user confirmation before proceeding. Grant proposals require PI-specific judgment at every stage. Set
trueonly if user explicitly requests fully autonomous mode.
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 Changed b7870c8f02db
- 12d ago First seen · 699 lines · 131 tokens per session scan A c0859beb700f
grant-proposal is a skill published in the GitHub repository wanshuiyin/Auto-claude-code-research-in-sleep (16,030 stars, last pushed today), licensed MIT. It adds 131 tokens to every session and 8,640 once invoked, about $0.0007 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
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…
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.
ligandmpnn
Inverse-fold a backbone with ligand, nucleic-acid, and metal context using LigandMPNN (Dauparas et al. 2023, github.com/dauparas/LigandMPNN). Reach for this skill to redesign the residues lining a binding pocket around a bound small molecule or cofactor, to design metal-coordinating sites where the geometry must be…
evo2
Score, embed, and generate DNA sequences with Evo 2, a long-context genomic foundation model. Use this skill when: (1) Computing per-nucleotide or per-sequence likelihoods for variant effect scoring, (2) Embedding genomic windows for downstream classification, (3) Generating DNA conditioned on a prefix, (4) Scoring…
memory
Cross-project research memory. Deep-dive past projects' notes, record corrections, and save cross-project insights across all Luxas research projects.
ml-training-recipes
Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning…