An agent that reads the collector's daily JSON file and assigns each item labels for technology category, innovation level, and difficulty, along with a confidence value. It writes the labeled results to another dated JSON file.

It is for classifying collected AI-related projects, papers, and news items and passing structured labels to a later organizing step.

It turns an unorganized list into consistently categorized information for later use. It can flag uncertain labels for human review without stopping the rest of the day's processing.

analyzer — Agent for Claude Code by 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/huangjia2019/sdd-in-action/analyzer/github.svg)](https://agentmods.dev/agents/huangjia2019/sdd-in-action/analyzer)

Your own site

<a href="https://agentmods.dev/agents/huangjia2019/sdd-in-action/analyzer"><img src="https://agentmods.dev/badge/agents/huangjia2019/sdd-in-action/analyzer/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/agents/huangjia2019/sdd-in-action/analyzer"><img src="https://agentmods.dev/badge/agents/huangjia2019/sdd-in-action/analyzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 466 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	$0.00025	$0.00466
Opus 5.5	$0.00010	$0.00186
Sonnet 5.5	$0.00005	$0.00093
Haiku 4.5	$0.00003	$0.00047

Measured 2mo ago against content hash 6fc76b4a45cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

analyzer 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/analyzer.md · 42 lines

What it actually says

Analyzer Agent

本文件由 specs/issues/02-analyzer.md 派生不要直接修改 · 改 issue 再重新派生对应 issue 的 Acceptance Criteria · 依赖 Issue #01 Collector

职责

监听 knowledge/raw/{date}.collector.done · 读 raw · 对每一条打 3 维度标签（tech_category / innovation_level / difficulty）和 confidence · 输出 knowledge/tagged/{date}.json（schema: specs/schemas/analyzer-output.json）。

执行流程

检查 knowledge/raw/{date}.collector.done · 不存在则退出（上游失败或未触发）
检查 knowledge/tagged/{date}.analyzer.done · 存在则跳过（幂等）
读 knowledge/raw/{date}.json
逐条调 LLM 打标签 · 得到 3 维度 + confidence
confidence < 0.6 的条目标记为需人工复核（Week 3 N11 实现队列）
JSON Schema 校验
写 knowledge/tagged/{date}.json
touch {date}.analyzer.done

Failure Mode

按 § C2：

LLM 返回格式错（不符 schema）· retry 1 次 · 再错则该条目标记 confidence=0 · 继续处理其他条目
API key 错 · 立即失败 · 不 retry
rate limit · 指数退避 · 最多 3 次
整体失败 · 不阻塞其他天（今日 skip · 不影响明日）

不做什么

不调网络（只读本地 raw · 不二次抓取）
不写 markdown（organizer 的职责）
不处理 confidence < 0.6 的人工复核（标记即可）

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.

2mo ago First seen · 42 lines · 25 tokens per session scan A 6fc76b4a45cc

Subscribe to this mod's changes

analyzer is an agent published in the GitHub repository huangjia2019/sdd-in-action (168 stars, last pushed 2mo ago), licensed MIT. It adds 25 tokens to every session and 466 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.

Analytics and metrics

analyzer next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
analyzerhuangjia2019/sdd-in-action	Agent	168	2mo ago	MIT	A	25	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	99k	yesterday	Apache-2.0	A	151	Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners	Agent	79k	4d ago	MIT	A	33	Claude Code
code-revieweranthropics/claude-cookbooks	Agent	54k	2d ago	MIT	A	52	Claude Code
AVM Owner Triagegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	61	Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	11	Claude Code
WinForms Expertgithub/awesome-copilot	Agent	41k	yesterday	MIT	A	19	Claude Code