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/auto-paper-improvement-loopWrote 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/auto-paper-improvement-loop)<a href="https://agentmods.dev/skills/wanshuiyin/auto-claude-code-research-in-sleep/auto-paper-improvement-loop"><img src="https://agentmods.dev/badge/skills/wanshuiyin/auto-claude-code-research-in-sleep/auto-paper-improvement-loop/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/auto-paper-improvement-loop"><img src="https://agentmods.dev/badge/skills/wanshuiyin/auto-claude-code-research-in-sleep/auto-paper-improvement-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- 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 Agent Snooping · line 474 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Excessive Agency · line 669 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.
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 | $0.00067 | $0.10089 |
| Opus 5 | $0.00034 | $0.05045 |
| Sonnet 5 | $0.00013 | $0.02018 |
| Haiku 4.5 | $0.00007 | $0.01009 |
Grade A, and why
auto-paper-improvement-loop 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:
- auto-paper-improvement-loop — 91% identical, 115 lines differ
How it starts
The opening of the file, as written. The whole thing — 696 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto Paper Improvement Loop: Review → Fix → Recompile
🔒 Do not wrap this skill in
/loop,/schedule, orCronCreate. It already loops internally (review → fix → recompile) with its own round structure and a deliberate fresh-reviewer bias guard each round (nocodex-reply). Re-asking it to "improve the paper" on a wall-clock timer produces no new signal — quality changes when the review changes, not when the clock ticks — and a timed re-run that also accepts its own output to decide when to stop crosses into self-acquittal (acceptance-gate.md). Schedule the external wait that precedes it, not the improvement loop. Seeshared-references/external-cadence.md.
Autonomously improve the paper at: $ARGUMENTS
Context
This skill is designed to run after Workflow 3 (/paper-plan → /paper-figure → /paper-write → /paper-compile). It takes a compiled paper and iteratively improves it through external LLM review.
Unlike /auto-review-loop (which iterates on research — running experiments, collecting data, rewriting narrative), this skill iterates on paper writing quality — fixing theoretical inconsistencies, softening overclaims, adding missing content, and improving presentation.
Constants
- MAX_ROUNDS = 2 — Two rounds of review→fix→recompile. Empirically, Round 1 catches structural issues (4→6/10), Round 2 catches remaining presentation issues (6→7/10). Diminishing returns beyond 2 rounds for writing-only improvements.
- REVIEWER_MODEL =
gpt-6-astra— Model used via Codex MCP for paper review. - REVIEWER_BIAS_GUARD = true — When
true, every review round uses a freshmcp__codex__codexthread with no prior review context. Never usemcp__codex__codex-replyfor review rounds. Set tofalseonly for deliberate debugging of the legacy behavior. Empirical evidence: running the same paper withcodex-reply+ "since last round we did X" prompts inflated scores from real 3/10 → fake 8/10 across multiple rounds; switching to fresh threads recovered the true 3/10 assessment. - REVIEW_LOG =
PAPER_IMPROVEMENT_LOG.md— Cumulative log of all rounds, stored in paper directory. - HUMAN_CHECKPOINT = false — When
true, pause after each round's review and present score + weaknesses to the user. The user can approve fixes, provide custom modification instructions, skip specific fixes, or stop early. Whenfalse(default), runs fully autonomously. - EDIT_WHITELIST =
null— Optional path to a YAML/JSON whitelist file constraining which paths and operations the fix-implementation step may touch. Whennull(default), all edits proceed unconstrained. When set via— edit-whitelist <path>(also accepts— edit_whitelist <path>), the loop loads the file at startup and consults it before each edit; rejected edits are logged toPAPER_IMPROVEMENT_LOG.mdrather than silently dropped. See "Optional: Edit Whitelist" below.
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 · -2 tokens per session 6472a47dae81
- 8d ago Changed · +22 lines cbc81c8c8049
- 12d ago First seen · 674 lines · 69 tokens per session scan A acc1114d7f6f
auto-paper-improvement-loop is a skill published in the GitHub repository wanshuiyin/Auto-claude-code-research-in-sleep (15,970 stars, last pushed 2d ago), licensed MIT. It adds 67 tokens to every session and 10,089 once invoked, about $0.0003 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
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.
paper-narrative
Judge and reshape the story told by an entire paper figure deck. Use when writing or revising a paper to derive a grounded brief from the manuscript and captions, review the full deck as a handling editor, and hand an ordered figure arc to figure-composer.
esmfold2
Biohub ESMFold2 / ESMFold2-Fast all-atom co-folding (Candido et al. 2026, github.com/Biohub/esm). Single-sequence and MSA modes; protein, DNA, RNA, ligand (CCD/SMILES), modified residues. FoldBench Ab-Ag 50-55%, PPI 70-77% DockQ-pass. Also covers the ESMC-{300M,600M,6B} protein language models from the same release…
literature-review
Find, verify, and synthesize scientific literature — from "what's the seminal paper for X" through full multi-source reviews. Covers grounding claims in real retrieved sources, avoiding fabricated citations, handling retractions, and calibrating confidence to evidence strength.
scvi-tools
Probabilistic single-cell RNA-seq with scvi-tools — scVI for a batch-corrected latent space, scANVI for semi-supervised label transfer, and Bayesian differential expression. Reach for this skill to integrate scRNA-seq batches, embed cells for clustering, transfer annotations from a reference onto a query, or score…
figure-composer
Compose one publication-grade multi-panel figure. Start from a one-line claim plus immutable data Artifact Version references, or inspect an existing figure and draft its outline directly. Plan a 12-column panel outline, delegate one worker per panel, compose and inspect the result, then run at most three adversarial…