research-watch

research-watch is a skill for Claude Code from kinhluan/skills. It costs 64 tokens per session (1,917 once invoked), scanned A, original, MIT.

A monitoring setup for finding new research papers, trends, and follow-up work about selected topics, authors, conferences, journals, or keywords. arXiv is a public repository for research preprints, and Semantic Scholar is a research-paper search service.

In plain words
What is it for?
Use it to watch research topics, specific researchers, or publication venues, receive recurring updates, rank papers by relevance, and decide what to read or skim.
Why use it?
It reduces the manual effort of repeatedly checking a fast-moving field and helps keep a literature review current.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the kinhluan-skills plugin — 61 skills shipped together

Good fit Use it to watch research topics, specific researchers, or publication venues, receive recurring updates, rank papers by relevance, and decide what to read or skim.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kinhluan/skills/research-watch
Install

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.

Any agent
npx skills add kinhluan/skills --skill research-watch
Clone the repo
git clone --depth 1 https://github.com/kinhluan/skills

Made for: Claude Code.

Or install kinhluan-skills, the plugin that ships this one along with the rest of its 61 skills.

Wrote 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.

agentmods badge for research-watch

README.md
[![agentmods](https://agentmods.dev/badge/skills/kinhluan/skills/research-watch/github.svg)](https://agentmods.dev/skills/kinhluan/skills/research-watch)
Your own site
<a href="https://agentmods.dev/skills/kinhluan/skills/research-watch"><img src="https://agentmods.dev/badge/skills/kinhluan/skills/research-watch/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.

agentmods 80×15 button for research-watch

Your own site · 80×15
<a href="https://agentmods.dev/skills/kinhluan/skills/research-watch"><img src="https://agentmods.dev/badge/skills/kinhluan/skills/research-watch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,917 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00064 $0.01917
Opus 5 $0.00032 $0.00958
Sonnet 5 $0.00013 $0.00383
Haiku 4.5 $0.00006 $0.00192

Measured 10d ago against content hash c638eebc4317, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

research-watch scanned grade A 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 10d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl "https://api.semanticscholar.org/graph/v1/paper/search?query=mechanistic+interpretability&fields=title,authors,year,abstract,citationCount&publicationDateOrYear=2024:2025"
.agent-skills/research-watch/SKILL.md · 267 lines

How it starts

The opening of the file, as written. The whole thing — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Watch

Stay current without drowning in papers.

Set up intelligent monitoring for research topics, authors, venues, or keywords. Get notified when relevant new work appears, with automatic relevance scoring and synthesis.

"The literature moves fast. Your knowledge should move faster." — Anonymous Researcher


1. Watch Types

1.1 Topic Watch

Monitor a research topic for new papers:

Topic: "mechanistic interpretability"
Keywords: ["mechanistic interpretability", "circuit tracing", "activation patching"]
Venues: [NeurIPS, ICML, ICLR, arXiv cs.LG]
Frequency: weekly

Relevance scoring:

Score Criteria Action
90-100 Directly addresses your research question Read immediately
70-89 Related method or application Read within 2 days
50-69 Same field, tangential topic Skim abstract
< 50 Same broad area Skip, but log for completeness

1.2 Author Watch

Track specific researchers:

Authors: ["Yann LeCun", "Yoshua Bengio", "Geoffrey Hinton"]
Rationale: "Foundational figures in deep learning"
Alert on: new papers, preprints, blog posts

1.3 Venue Watch

Monitor specific conferences/journals:

Venues: ["NeurIPS", "ICML", "ICLR", "JMLR"]
Filter: papers matching [your keywords]
Alert: when proceedings published

1.4 Citation Watch

Track who cites your work or key papers:

Target papers: [your-paper-id, foundational-paper-id]
Alert on: new citations
Include: citation context (how they cite you)

2. Setup Protocol

Step 1 — Define Watch Scope

Watch Name: [descriptive name]
Type: [topic / author / venue / citation]
Query: [keywords, authors, or paper IDs]
Sources: [arXiv / Semantic Scholar / Google Scholar / PubMed]
Frequency: [daily / weekly / monthly]

Step 2 — Configure Filters

Exclude noise:

  • Negative keywords: ["survey", "review", "tutorial"] (if you want only original research)
  • Minimum citations: [0 for new work, 10 for established work]
  • Date range: [last 30 days / last 90 days / all time]

Read the full file on GitHub · 267 lines

Files

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.

Changes

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.

  1. 10d ago First seen · 267 lines · 64 tokens per session scan A c638eebc4317

Subscribe to this mod's changes

research-watch is a skill published in the GitHub repository kinhluan/skills (4 stars, last pushed 13d ago), licensed MIT. It adds 64 tokens to every session and 1,917 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

domain-driven-design

DDD tactical patterns for complex business modeling including entities, value objects, aggregates, domain services, repositories, specifications, and bounded contexts. Python dataclass implementations with TypeScript alternatives. Use when building rich domain models, enforcing invariants, or separating domain logic…

yonatangross/orchestkit · 57 tokens

ideogram-ultra

Build Ideogram 4 (Ideogram Ultra) txt2img and img2img workflows with the local open-weights model, dual conditional/unconditional models with DualModelGuider, Qwen3-VL text encoder, and structured JSON ("compositional deconstruction") prompts for strong text rendering and layout control.

artokun/comfyui-mcp · 68 tokens

flux-txt2img

Build Flux txt2img workflows with Flux.1 Dev (SRPO), Flux 2 Klein 9B, Turbo LoRAs, FluxGuidance, and DualCLIPLoader patterns.

artokun/comfyui-mcp · 44 tokens

panel-node-pack-sync

Keep the ComfyUI sidebar panel node-pack (comfyui-agent-panel) in step with the orchestrator after comfyui-mcp updates. Use this whenever the orchestrator was just updated (installcomfyui (action:"selfupdate"), npm i -g comfyui-mcp, a new version in the ENVIRONMENT line), when a panel/bridge command fails in a way…

artokun/comfyui-mcp · 206 tokens

civitai

Discover Civitai models with the BUILT-IN downloadmodel action:"searchcivitai" and install/generate them locally. Find a checkpoint/LoRA/embedding on Civitai, download it into ComfyUI, and use its trigger words. Optionally pair the official Civitai MCP for community features (images browsing, posting, collections).

artokun/comfyui-mcp · 76 tokens

chief-strategy-officer

Owns where the business plays and how it wins over a multi-year horizon — portfolio choices, corporate development, strategic partnerships, and planning under uncertainty. Use this for a decision about which markets or businesses to be in, whether to build, buy, or partner, how to allocate capital across business…

cbrock84/headcount · 93 tokens