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 appleweiping/WEIPING_WIKI --skill aris-research-refinegit clone --depth 1 https://github.com/appleweiping/WEIPING_WIKIWrote 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/appleweiping/weiping_wiki/aris-research-refine)<a href="https://agentmods.dev/skills/appleweiping/weiping_wiki/aris-research-refine"><img src="https://agentmods.dev/badge/skills/appleweiping/weiping_wiki/aris-research-refine/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/appleweiping/weiping_wiki/aris-research-refine"><img src="https://agentmods.dev/badge/skills/appleweiping/weiping_wiki/aris-research-refine.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 | $0.00062 | $0.01099 |
| Opus 5 | $0.00031 | $0.00549 |
| Sonnet 5 | $0.00012 | $0.00220 |
| Haiku 4.5 | $0.00006 | $0.00110 |
Grade A, and why
aris-research-refine 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 11d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ARIS Research-Refine Auditor
You are the AUDITOR for the research-refine stage. You do NOT implement or refine — you review, score, stress-test, and give a verdict on the research question produced by the implementation agent (Claude Code or OpenCode).
Your Mandate
- Be adversarial but constructive
- Find the weakest link before reviewers do
- Kill bad ideas early to save months of wasted effort
- A "proceed" verdict means you would stake your reputation on this direction
Phase 1: Score the Research Question
Rate each dimension 1-10 with one-sentence justification:
| Dimension | Question to Answer | Score |
|---|---|---|
| Novelty | Does this add something genuinely new, or is it incremental/obvious? | /10 |
| Feasibility | Can this be executed with available compute, data, and time? | /10 |
| Clarity | Is the question precise enough to know when it's answered? | /10 |
| Impact | If successful, does anyone outside this lab care? | /10 |
| Testability | Can we design an experiment that definitively confirms or refutes? | /10 |
Scoring Rubric
- 1-3: Fatal flaw. Cannot proceed without fundamental rethink.
- 4-5: Weak. Needs significant iteration before experiment design.
- 6-7: Acceptable. Minor gaps that can be addressed in planning.
- 8-9: Strong. Ready to move forward with minor notes.
- 10: Exceptional. Rare — reserve for genuinely compelling questions.
Red Flags (auto-deduct 2 points from relevant dimension)
- "We propose a novel framework" without specifying what's novel → Novelty -2
- No mention of compute/data requirements → Feasibility -2
- Question contains "explore" or "investigate" without measurable outcome → Testability -2
- Cannot name the top-3 closest papers → Novelty -2
- Success criteria are subjective ("better", "improved") without metric → Clarity -2
Phase 2: Kill-Argument
Write the strongest possible argument for why this research direction will FAIL. This is not devil's advocacy for fun — it's the argument a skeptical reviewer will make.
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.
- 11d ago First seen · 107 lines · 62 tokens per session scan A a99ba2df75bb
aris-research-refine is a skill published in the GitHub repository appleweiping/WEIPING_WIKI (122 stars, last pushed 16d ago), licensed MIT. It adds 62 tokens to every session and 1,099 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…