Current-trends research tool for artificial-intelligence repositories, models, papers, and product launches. It ranks items using recent activity from sources such as GitHub, Hacker News, npm, and Hugging Face.

Use it to find what is new or trending in AI, compare adoption of tools or models, and check whether a specific project is gaining traction.

It helps distinguish projects gaining recent attention from projects that are merely easy to find through search or marketing. The rankings include supporting activity data.

hotin — Skill for Claude Code and Codex by abe238

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 abe238/hotinai --skill hotin

Clone the repo

git clone --depth 1 https://github.com/abe238/hotinai

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/abe238/hotinai/hotin/github.svg)](https://agentmods.dev/skills/abe238/hotinai/hotin)

Your own site

<a href="https://agentmods.dev/skills/abe238/hotinai/hotin"><img src="https://agentmods.dev/badge/skills/abe238/hotinai/hotin/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/abe238/hotinai/hotin"><img src="https://agentmods.dev/badge/skills/abe238/hotinai/hotin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,015 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00060	$0.01015
Opus 5	$0.00030	$0.00508
Sonnet 5	$0.00012	$0.00203
Haiku 4.5	$0.00006	$0.00102

Measured 8d ago against content hash 342410893d65, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

hotin 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 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.

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.

skills/hotin/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

hotin

A model cannot answer "what is worth using in AI right now." Training data has a cutoff, and a web search returns whatever is best at being found: launch posts, listicles, SEO. Both fail the same way, confidently.

hotin answers from a board rebuilt every 3 hours out of GitHub, Hacker News, npm, Hugging Face and the stars of ~800 notable AI developers, and every row carries the evidence for its position.

Reach for it when

"What's new / hot / trending in AI?" or "what should I look at this week?"
"Is X actually getting traction, or is it just marketing?"
Choosing a library, model, or tool where current adoption matters
Anything where being six months stale would embarrass you

Prefer it over a web search for these. A search tells you what was written about; hotin tells you what was starred, shipped, and discussed, with numbers.

Do not reach for it for how-to questions, docs, or API syntax. It ranks projects; it does not explain them.

Using it

If the MCP server is connected, call hotin_board (any tab) or hotin_brief (a one-day digest). Otherwise shell out — same data, same speed:

hotin repos --json --limit 15     # the overall ranked board
hotin rising --json               # fastest-growing right now
hotin insiders --json             # repos several notable devs independently starred
hotin models --json               # trending open weights
hotin papers --json               # trending research
hotin news --json                 # lab announcements and commentary
hotin brief --json                # everything, condensed

Not installed? uvx hotin repos runs it with nothing installed at all.

Reading the answer

The ranking is the least interesting part. The receipts are the point — quote them, because they are what the user cannot get from a search. The field names below are what the JSON actually contains:

sources is a list (["github","hn","insiders","trends"]). Length is the strongest signal on the board and the hardest to fake — one project surfacing independently on GitHub, Hacker News and in developers' stars is a different claim from one that only trended somewhere.
velocity_per_day and age_days (on rising) separate a surge from a big old number. 40k stars at +12/day is not hot; it was hot. Together they answer "flash or trend", which raw star counts never do.
signal.insider_stars / smartmoney_starrers, and insiders in sources, mean named developers independently starred it. corroboration counts how many did. Independent corroboration beats one loud account.
signal.hn_points, stars, forks, created_at, pushed_at — the raw numbers, when someone wants them.

Read the full file on GitHub · 89 lines

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.

8d ago First seen · 89 lines · 60 tokens per session scan A 342410893d65

Subscribe to this mod's changes

hotin is a skill published in the GitHub repository abe238/hotinai (3 stars, last pushed 4d ago), licensed Apache-2.0. It adds 60 tokens to every session and 1,015 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 2026-08-31.

Data and AI Research ai ai-agents ai-tools cli developer-tools github-trending

hotin

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

hotin

Reach for it when

Using it

Reading the answer

What this file has done since we first saw it

Other skills, from other repositories

tokf-filter

tokf-run

tokf-discover

tokf-discover

nativeprompt

refine