ai-radar

ai-radar is a skill for Claude Code from orzazade/awesome-ai-radar. It costs 106 tokens per session (4,284 once invoked), scanned A, original, MIT.

An AI-trend research tool with modes for personalised briefings, topic deep dives, and contributions to a shared AI news list. It first synchronises with that project's sources and data rules.

In plain words
What is it for?
Getting an AI news briefing, researching a specific AI topic, and preparing a contribution to the awesome-ai-radar project.
Why use it?
It helps developers catch up on relevant AI changes and keeps community contributions aligned with the list's required format.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; names the AskUserQuestion tool.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node scripts/generate-digest.js.

Good fit Getting an AI news briefing, researching a specific AI topic, and preparing a contribution to the awesome-ai-radar project.

Compare 6 skills from other repositories ↓
Install

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.

Clone the repo
git clone --depth 1 https://github.com/orzazade/awesome-ai-radar
agentmods
npx agentmods add skills/orzazade/awesome-ai-radar/ai-radar

Made for: Claude Code.

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 ai-radar

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/orzazade/awesome-ai-radar/ai-radar"><img src="https://agentmods.dev/badge/skills/orzazade/awesome-ai-radar/ai-radar.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,284 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00106 $0.04284
Opus 5 $0.00053 $0.02142
Sonnet 5 $0.00021 $0.00857
Haiku 4.5 $0.00011 $0.00428

Measured 11d ago against content hash bc85cf0d822e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ai-radar 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.

skill/ai-radar/SKILL.md · 452 lines

How it starts

The opening of the file, as written. The whole thing — 452 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Radar Skill

You are an AI trends researcher. You help the user stay current on AI developments, contribute to the awesome-ai-radar community list, and deep-dive into specific topics.

Mode Detection

Parse the arguments after /ai-radar:

  • briefing or no argumentsBriefing mode
  • contributeContribute mode
  • catch-up [topic] or catchup [topic]Catch-up mode (extract everything after catch-up as the topic)

If the argument does not match any mode, ask the user which mode they intended.


Step 0 — Project Sync (ALL modes, run FIRST)

Before any research, sync with the awesome-ai-radar project to get the schema, sources, and existing entries.

0A. Locate the repo

Try these locations in order:

  1. Check if cwd is inside awesome-ai-radar (check for schema/entry.schema.json)
  2. ~/Projects/scifi/awesome-ai-radar/
  3. /tmp/awesome-ai-radar-contribute/
  4. If not found, clone: gh repo clone orzazade/awesome-ai-radar /tmp/awesome-ai-radar-contribute

Set RADAR_DIR to the found path.

0B. Read the schema

Read $RADAR_DIR/schema/entry.schema.json. Extract:

  • Valid categories: from properties.category.enum (currently: Model Release, Tool, Framework, Paradigm, Infrastructure, Research)
  • Valid signals: from properties.signal.enum
  • Required fields: from required array
  • Optional fields: rising, stars, repo_url, radar_quadrant, radar_ring

NEVER hardcode categories — always read them from the schema. This ensures the skill stays in sync even if the schema changes.

0C. Read the source registry

Read $RADAR_DIR/src/_data/sources.json. This is a curated list of primary sources (official changelogs, release pages, blogs). Use these in research.

0D. Build dedup index (contribute mode only)

Determine the current ISO week: date +%Y-W%V → e.g., 2026-W12. Read all .md files in $RADAR_DIR/src/pulse/YYYY/WXX/ (excluding digest.md). Extract titles and topics from frontmatter. Store as dedup index.

Read the full file on GitHub · 452 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.

  1. 11d ago First seen · 452 lines · 106 tokens per session scan A bc85cf0d822e

Subscribe to this mod's changes

ai-radar is a skill published in the GitHub repository orzazade/awesome-ai-radar (2 stars, last pushed 5mo ago), licensed MIT. It adds 106 tokens to every session and 4,284 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 83 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens