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/paper-writingWrote 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/paper-writing)<a href="https://agentmods.dev/skills/wanshuiyin/auto-claude-code-research-in-sleep/paper-writing"><img src="https://agentmods.dev/badge/skills/wanshuiyin/auto-claude-code-research-in-sleep/paper-writing/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/paper-writing"><img src="https://agentmods.dev/badge/skills/wanshuiyin/auto-claude-code-research-in-sleep/paper-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
- Snyk warn
- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
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 →
- high Agent Snooping · line 814 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- medium Rogue Agent · line 675 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.
- medium Excessive Agency · line 896 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 | $0.00058 | $0.13148 |
| Opus 5.5 | $0.00023 | $0.05259 |
| Sonnet 5.5 | $0.00012 | $0.02630 |
| Haiku 4.5 | $0.00006 | $0.01315 |
Grade B, and why
paper-writing scanned grade B with 1 finding 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 8d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
in `~/.claude/settings.json`: Copies of this mod
1 near-identical copy found in the catalogue:
- paper-writing — 88% identical, 326 lines differ
How it starts
The opening of the file, as written. The whole thing — 943 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow 3: Paper Writing Pipeline
Before each reviewer slot, follow Selectable Reviewers: resolve invocation →
.aris/reviewer.json→ Claude Code default (Codex MCP) withreviewer_route.pythrough the canonical helper resolver, preserving this slot's tier, fresh contexts, source/image inputs and deterministic gates. Codex examples/pins below apply only tobackend=codex; other routes use their own first-call/reply contract. Save the route and actual returned identity; unavailable selections areREVIEW_UNAVAILABLE. Classify acceptance from actual families/completion/scope. Forward invocation reviewer/model/effort overrides to reviewer-bearing children. Generation workers are unchanged.
Orchestrate a complete paper writing workflow for: $ARGUMENTS
Overview
This skill chains five sub-skills into a single automated pipeline:
/paper-plan → /paper-figure → /paper-write → /paper-compile → /auto-paper-improvement-loop
(outline) (plots) (LaTeX) (build PDF) (review & polish ×2)
Each phase builds on the previous one's output. The final deliverable is a polished, reviewed paper/ directory with LaTeX source and compiled PDF.
In this hybrid pack, the pipeline itself is unchanged, but paper-plan and paper-write use Orchestra-adapted shared references for stronger story framing and prose guidance.
Constants
- VENUE =
ICLR— Target venue. Options:ICLR,NeurIPS,ICML,CVPR,ACL,AAAI,ACM,IEEE_JOURNAL(IEEE Transactions / Letters),IEEE_CONF(IEEE conferences). Affects style file, page limit, citation format. - MAX_IMPROVEMENT_ROUNDS = 2 — Number of review→fix→recompile rounds in the improvement loop.
- REVIEWER_MODEL =
gpt-6-astra— Model used via Codex MCP for plan review, figure review, writing review, and improvement loop. - AUTO_PROCEED = true — Auto-continue between phases. Set
falseto pause and wait for user approval after each phase. - HUMAN_CHECKPOINT = false — When
true, the improvement loop (Phase 5) pauses after each round's review to let you see the score and provide custom modification instructions. Whenfalse(default), the loop runs fully autonomously. Passed through to/auto-paper-improvement-loop. - ILLUSTRATION =
figurespec— Architecture/illustration generator for Phase 2b:figurespec(default, deterministic JSON→SVG via/figure-spec, best for architecture/workflow/topology),gemini(AI-generated via/paper-illustration, best for qualitative method illustrations; needsGEMINI_API_KEY),codex-image2(AI-generated via/paper-illustration-image2through the local Codex native image bridge — no external API key, uses your ChatGPT Plus/Pro quota; experimental),mermaid(Mermaid syntax via/mermaid-diagram, free, best for flowcharts), orfalse(skip Phase 2b, manual only).
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.
- 8d ago Changed · +13 lines 597ad9adc415
- 1mo ago Changed 310a9b29b686
- 1mo ago Changed · +4 lines 986a0f1a930d
- 1mo ago First seen · 926 lines · 58 tokens per session scan B 153f2bf0c696
paper-writing is a skill published in the GitHub repository wanshuiyin/Auto-claude-code-research-in-sleep (18,176 stars, last pushed 3d ago), licensed MIT. It adds 58 tokens to every session and 13,148 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
privacy-by-design
Use when building apps that collect user data. Ensures privacy protections are built in from the start—data minimization, consent, encryption.
ethics-committee
Act as a research ethics committee — stress-test a protocol the way an IRB / REC / HREC would. Reviews informed consent, risk-benefit balance, vulnerable populations, data privacy, deception, debriefing, payment, dual-use risks, AI/LLM use in research, and equity in recruitment. Produces a committee-style decision…
freelance-dev-sow
When to use. A potential client wants a fixed-scope software project and needs a one-page SOW before they sign + pay deposit.
advogado-criminal
Advogado criminalista especializado em Maria da Penha, violencia domestica, feminicidio, direito penal brasileiro, medidas protetivas, inquerito policial e acao penal.
advogado-especialista
Advogado especialista em todas as areas do Direito brasileiro: familia, criminal, trabalhista, tributario, consumidor, imobiliario, empresarial, civil e constitucional.
fto-triage
Freedom-to-operate triage — a structured first look at potentially blocking patents, not an FTO opinion. Use when a product, process, or feature is being evaluated for blocking patents, when asked whether anything stops a launch, or to build a claim-chart first pass against the most plausible patents before patent…