What is agents-radar AGENTS.md?

Project instructions for agents-radar, a daily digest tool for AI open-source projects. They document the project, commands, testing, formatting, GitHub Actions, and supported language-model providers.

Use them when developing, testing, formatting, or running the digest generator locally. They also help configure its language-model provider and optional GitHub issue publishing.

They give a coding agent the context and commands needed to work in the repository without guessing. They also explain which environment variables are needed for local runs.

agents-radar AGENTS.md — Instructions file for Codex and OpenCode by duanyytop: Project instructions for agents-radar, a daily digest tool f

About the project

agents-radar is an automated GitHub Actions workflow that gathers AI-related updates from sources such as GitHub, ArXiv, Hacker News, Hugging Face, and Product Hunt, then publishes bilingual daily digests. Developers and AI enthusiasts use its issues, Markdown reports, web interface, RSS feed, and messaging notifications to follow the ecosystem. The catalogue instructions relate to running or using this reporting workflow.

duanyytop/agents-radar · 1,044 stars · on GitHub

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.

agentmods

npx agentmods add instructions/duanyytop/agents-radar/agents-md

Clone the repo

git clone --depth 1 https://github.com/duanyytop/agents-radar

Made for: Codex, OpenCode.

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/instructions/duanyytop/agents-radar/agents-md.svg)](https://agentmods.dev/instructions/duanyytop/agents-radar/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/duanyytop/agents-radar/agents-md"><img src="https://agentmods.dev/badge/instructions/duanyytop/agents-radar/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 2,780 This file is loaded in full into every session.

When invoked 2,780 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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	$0.02780	$0.02780
Opus 5	$0.01390	$0.01390
Sonnet 5	$0.00556	$0.00556
Haiku 4.5	$0.00278	$0.00278

Measured 5d ago against content hash 3a67e68ae7e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agents-radar AGENTS.md 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 5d 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.

AGENTS.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Project overview

agents-radar is a daily digest generator for the AI open-source ecosystem. A GitHub Actions cron job runs at 00:00 UTC (08:00 CST) and produces bilingual (Chinese + English) reports, published as GitHub Issues and committed Markdown files.

Commands

pnpm start          # run the full digest locally
pnpm test           # vitest (unit tests)
pnpm typecheck      # tsc --noEmit
pnpm lint           # ESLint
pnpm lint:fix       # ESLint --fix
pnpm format         # Prettier --write src
pnpm format:check   # Prettier --check src

Required env vars for local runs:

export GITHUB_TOKEN=ghp_xxxxx
export DIGEST_REPO=owner/repo   # omit to skip GitHub issue creation

# LLM provider (default: anthropic)
export LLM_PROVIDER=anthropic   # anthropic | openai | github-copilot | openrouter | deepseek

# Anthropic (default)
export ANTHROPIC_API_KEY=sk-ant-xxxxx

# OpenAI
# export OPENAI_API_KEY=sk-xxxxx

# GitHub Copilot — uses GITHUB_TOKEN

# OpenRouter
# export OPENROUTER_API_KEY=sk-or-xxxxx

# DeepSeek
# export DEEPSEEK_API_KEY=sk-xxxxx

Architecture

The pipeline runs in four sequential phases, each implemented as a named async function in src/index.ts:

fetchAllData — all network I/O in parallel: GitHub API (issues/PRs/releases) for 17 repos, Claude Code Skills, Anthropic/OpenAI sitemaps, GitHub Trending HTML + Search API, Hacker News Algolia API.
generateSummaries — per-repo LLM calls, all in parallel, rate-limited to 5 concurrent requests by a queue in src/report.ts.
Comparisons — two LLM calls: cross-tool CLI comparison and OpenClaw cross-ecosystem comparison.
Save phase — buildCliReportContent / buildOpenclawReportContent / buildInfraReportContent (in src/report-builders.ts) build Markdown strings; saveWebReport / saveTrendingReport / saveHnReport (in src/report-savers.ts) call LLM + write file + create GitHub Issue.

Source files

File	Responsibility
`src/index.ts`	Orchestration: repo config, phase functions, `main()`
`src/i18n.ts`	Centralized bilingual strings: `Lang` type, report titles, issue labels, footer text, `REPORT_LABELS`, `NOTIFY_LABELS`
`src/github.ts`	GitHub API helpers: `fetchRecentItems`, `fetchRecentReleases`, `fetchRecentDiscussions` (GraphQL), `fetchSkillsData`, `createGitHubIssue`; shared `RepoFetch` type
`src/config.ts`	Loads `config.yml` into `RadarConfig` (`cliRepos`, `skillsRepo`, `openclaw`, `openclawPeers`, `infraRepos`); built-in defaults when a section is missing
`src/prompts.ts`	LLM prompt builders for repo reports: `buildCliPrompt`, `buildPeerPrompt`, `buildInfraPrompt`, `buildComparisonPrompt`, `buildInfraComparisonPrompt`, `buildPeersComparisonPrompt`, `buildSkillsPrompt`
`src/prompts-data.ts`	LLM prompt builders for data-source reports: `buildTrendingPrompt`, `buildWebReportPrompt`, `buildHnPrompt`
`src/report.ts`	`callLlm` (with concurrency limiter), `saveFile`, `autoGenFooter` (uses i18n), LLM token budget constants
`src/report-builders.ts`	`buildCliReportContent`, `buildOpenclawReportContent`, `buildInfraReportContent` — assemble final Markdown strings for CLI, OpenClaw and infra reports
`src/report-savers.ts`	`saveWebReport`, `saveTrendingReport`, `saveHnReport` — LLM call + file save + optional GitHub issue
`src/date.ts`	Date and timing utilities: `toCstDateStr`, `toUtcStr`, `sleep`
`src/providers/types.ts`	`LlmProvider` interface, `ProviderName` type, `VALID_PROVIDER_NAMES`
`src/providers/openai-compatible.ts`	`OpenAICompatibleProvider` — shared base class for OpenAI-compatible providers
`src/providers/anthropic.ts`	`AnthropicProvider` — Anthropic SDK wrapper
`src/providers/openai.ts`	`OpenAIProvider` — extends `OpenAICompatibleProvider`
`src/providers/github-copilot.ts`	`GitHubCopilotProvider` — extends `OpenAICompatibleProvider`
`src/providers/openrouter.ts`	`OpenRouterProvider` — extends `OpenAICompatibleProvider`
`src/providers/deepseek.ts`	`DeepSeekProvider` — extends `OpenAICompatibleProvider`
`src/providers/index.ts`	`createProvider` factory + barrel re-exports
`src/web.ts`	Sitemap-based web content fetching; state persisted to `digests/web-state.json`
`src/trending.ts`	GitHub Trending HTML scraper + Search API topic queries
`src/hn.ts`	Hacker News top AI stories via Algolia HN Search API
`src/generate-manifest.ts`	Generates `manifest.json` (sidebar data for Web UI) and `feed.xml` (RSS 2.0 feed)

Read the full file on GitHub · 137 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.

5d ago First seen · 137 lines · 2,780 tokens per session scan A 3a67e68ae7e8

Subscribe to this mod's changes

agents-radar AGENTS.md is an instructions file published in the GitHub repository duanyytop/agents-radar (1,044 stars, last pushed today), licensed MIT. It adds 2,780 tokens to every session, about $0.0139 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.

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

agents-radar AGENTS.md

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

AGENTS.md

Project overview

Commands

Architecture

Source files

What this file has done since we first saw it

Other instructions, from other repositories

vscode buildNext.instructions.md

spec-kit AGENTS.md

codex AGENTS.md

vscode oss-third-party-notices.instructions.md

langchain AGENTS.md

deepseek-harness AGENTS.md