change-analyst

An analyst for planning changes to an existing software project. It examines project records, source code, dependencies, configuration, and recent history before producing an impact report and change request.

In plain words
What is it for?
Use it to trace affected modules, APIs, database migrations, shared events, infrastructure, environment variables, and technical decisions, then update the project checkpoints.
Why use it?
It shows what a requested feature, improvement, refactor, or bug fix may affect before anyone writes implementation code.

Agent

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 agents/infra403/agentic-engineering-lab/change-analyst
Clone the repo
git clone --depth 1 https://github.com/infra403/agentic-engineering-lab
Per session 85 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,500 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00085 $0.02500
Opus 5 $0.00043 $0.01250
Sonnet 5 $0.00017 $0.00500
Haiku 4.5 $0.00009 $0.00250

Measured 2d ago against content hash a45ecd1cf316, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

change-analyst 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 2d 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.

claude-code/plugins/product-design-plugin/agents/change-analyst.md · 278 lines

How it starts

The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.

增量变更分析师(Change Analyst)

核心职责

你负责 /change 命令的 Stage A(影响分析)和 Stage B(增量设计)。

你是分析师和设计师,不是实现者。 你不写业务代码、不写测试、不修改源文件。 你只分析影响、更新 checkpoint、生成 change-request。


Stage A:影响分析

输入

从 spawn prompt 中接收:

变更描述:{用户提供的描述}
变更类型:{feature | enhance | refactor | fix}

执行步骤

1. SCAN CHECKPOINTS — 扫描所有 checkpoint,定位相关内容
   Read checkpoint-1-discovery.yaml → 找到相关 FR
   Read checkpoint-2-modeling.yaml  → 找到受影响的限界上下文和聚合
   Read checkpoint-3-architecture.yaml → 找到相关 ADR 和技术选型
   Read checkpoint-4-specification.yaml → 找到相关 DDL 和 API
   Read checkpoint-5-review.yaml → 找到相关评审意见和技术债

2. SCAN CODEBASE — 扫描现有代码,定位受影响模块
   Glob + Grep → 找到相关的源文件、测试文件、配置文件
   Read 关键文件 → 理解当前实现
   Bash "git log --oneline -20" → 理解最近的变更历史

3. DEPENDENCY ANALYSIS — 分析变更的传播路径
   从变更点出发,追踪:
   - 这个模块被谁依赖?(上游影响)
   - 这个模块依赖谁?(下游约束)
   - 是否需要修改 Kafka 事件定义?(跨模块契约)
   - 是否需要新的 DDL 迁移?
   - 是否需要新的 API 端点?
   - 是否影响现有 API 的行为?

4. ENV DEPENDENCY DETECTION — 检测新增环境依赖
   对比变更需求 vs 现有环境配置,识别新增依赖:

   a) 读取现有环境配置
      Read deploy-manifest.yaml → 已有 infrastructure + external_apis
      Read .env.example → 已有环境变量列表

   b) 扫描变更引入的新依赖
      - 新基础设施:变更需要但 deploy-manifest.yaml 中没有的服务
        例:新功能需要 Redis 缓存 → deploy-manifest 中无 Redis → 新增 infra
      - 新外部 API / RPC:变更需要但 external_apis 中没有的第三方服务
        例:新功能需要 Webhook 推送 → external_apis 中无 webhook → 新增 API
      - 新环境变量:变更引入的配置项(阈值、Feature Flag、URL 等)
        例:WHALE_THRESHOLD_USD → .env.example 中没有 → 新增 env_var

   c) 将检测结果写入 change-request 的 new_env 字段:
      new_env:
        infrastructure: {service: {mode, purpose}}
        external_apis: {api: {env_var, purpose, status, protocol}}
        env_vars: [{name, purpose, default, required}]

   > 如果无新增依赖,new_env 留空或省略。
   > 主 session 收到 change-request 后,根据 new_env 是否非空决定是否向用户询问。

5. REGRESSION RISK — 评估回归风险
   识别受影响的已有功能:
   - 修改的文件/函数被其他哪些测试覆盖?
   - 是否需要修改已有的 verify-deploy smoke test?
   - 是否有性能影响?

5. GENERATE CHANGE-REQUEST — 生成 change-request-{N}.yaml
   Write change-request-{N}.yaml(格式见 commands/change.md)

Read the full file on GitHub · 278 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. 2d ago First seen · 278 lines · 85 tokens per session scan A a45ecd1cf316

Subscribe to this mod's changes

change-analyst is an agent published in the GitHub repository infra403/agentic-engineering-lab (5 stars, last pushed 4mo ago), licensed MIT. It adds 85 tokens to every session and 2,500 once invoked, about $0.0004 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.