agentmods.dev

collector

collector is an agent for Claude Code from huangjia2019/sdd-in-action. It costs 28 tokens per session (500 once invoked), scanned A, original, MIT.

An agent that collects the day's top GitHub Trending repositories, Hacker News items, and arXiv papers, then keeps entries related to AI, language models, agents, or machine learning. It saves the filtered results as a dated JSON file.

In plain words
What is it for?
It is for building a daily technology feed from GitHub Trending, Hacker News, and arXiv, with structured output that another process can analyze.
Why use it?
It removes the manual work of checking several sources and filtering out unrelated items. It also records failures and avoids repeating a collection that has already completed.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

not rated 168repo +3 2mo ago A scan 28 tokens original MIT

Good fit It is for building a daily technology feed from GitHub Trending, Hacker News, and arXiv, with structured output that another process can analyze.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/huangjia2019/sdd-in-action/collector
View source ↗ huangjia2019/sdd-in-action
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.

Clone the repo
git clone --depth 1 https://github.com/huangjia2019/sdd-in-action

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 collector

README.md
[![agentmods](https://agentmods.dev/badge/agents/huangjia2019/sdd-in-action/collector/github.svg)](https://agentmods.dev/agents/huangjia2019/sdd-in-action/collector)
Your own site
<a href="https://agentmods.dev/agents/huangjia2019/sdd-in-action/collector"><img src="https://agentmods.dev/badge/agents/huangjia2019/sdd-in-action/collector/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 collector

Your own site · 80×15
<a href="https://agentmods.dev/agents/huangjia2019/sdd-in-action/collector"><img src="https://agentmods.dev/badge/agents/huangjia2019/sdd-in-action/collector.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 500 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 $0.00028 $0.00500
Opus 5.5 $0.00011 $0.00200
Sonnet 5.5 $0.00006 $0.00100
Haiku 4.5 $0.00003 $0.00050

Measured 2mo ago against content hash 8267e8812462, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

collector 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 2mo 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.

week1/code/03/agents/collector.md · 44 lines

What it actually says

Collector Agent

本文件由 specs/issues/01-collector.md 派生 不要直接修改 · 改 issue 再重新派生 对应 issue 的 Acceptance Criteria · 含数据契约 / 完成标记 / 失败处理 / 幂等性 / 可观测性

职责

每天 UTC 0:00 触发，抓 GitHub Trending Top 50，过滤 topics 包含 ai/llm/agent/ml 的 repo，输出 knowledge/raw/{date}.json（schema: specs/schemas/collector-output.json）。

执行流程

  1. 读 knowledge/raw/{date}.collector.done · 存在则跳过（幂等 · 除非 --force）
  2. WebFetch https://github.com/trending · 解析 top 50
  3. 按 topics 过滤 AI 相关
  4. 通过 JSON Schema 校验
  5. 写 knowledge/raw/{date}.json
  6. touch knowledge/raw/{date}.collector.done

Failure Mode

按 specs/issues/01-collector.md 的 Acceptance Criteria § 失败处理 执行：

  • HTTP 5xx 或网络抖动 · retry 3 次（指数退避 1s/4s/16s）
  • rate limit 429 · 按 Retry-After header 等待 · 最多 5 次
  • 401/403（auth 错误）· 立即失败 · 写 {date}.collector.failed · 不 retry
  • 最终失败 · 写 knowledge/incidents/{date}.md 记录详情

日志

按 § D1：start/end 写 knowledge/logs/{date}.log，字段 start_ts / end_ts / item_count / filtered_count。

不做什么

  • 不去重（由 analyzer 下游处理）
  • 不打标签（analyzer 的职责）
  • 不调 GitHub API（走 HTML 解析 · 避 rate limit）
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. 2mo ago First seen · 44 lines · 28 tokens per session scan A 8267e8812462

Subscribe to this mod's changes

collector is an agent published in the GitHub repository huangjia2019/sdd-in-action (168 stars, last pushed 2mo ago), licensed MIT. It adds 28 tokens to every session and 500 once invoked, about $0.0001 per session on Opus 5.5. 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.

Data and AIResearch
Related

collector compared with agents from other repositories

collector next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
collectorhuangjia2019/sdd-in-actionAgent1682mo agoMITA28Claude Code
Prompt Buildergithub/awesome-copilotAgent41kyesterdayMITA24Claude Code
fitjeremylongshore/tons-of-skills-marketplaceAgent2.9kyesterdayMITA57Claude Code
mlops-engineerpjt222/agent-almanacAgent43yesterdayMITA31Claude Code
migration-reviewerahmedawan-oracle/claude-code-pluginsAgent43mo agoMITA70Claude Code
openai-api-expert0xfurai/claude-code-subagentsAgent1.0k1y agoMITA23Claude Code
image-prompt-engineer18771050470/big-genius-skillsAgent102mo agononeA32Claude Code