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.
npx agentmods add commands/infra403/agentic-engineering-lab/changegit clone --depth 1 https://github.com/infra403/agentic-engineering-labWhat 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 | $0.00083 | $0.03988 |
| Opus 5 | $0.00042 | $0.01994 |
| Sonnet 5 | $0.00017 | $0.00798 |
| Haiku 4.5 | $0.00008 | $0.00399 |
Grade A, and why
change 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.
How it starts
The opening of the file, as written. The whole thing — 437 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/change 命令
核心理念
先设计再实现，先影响分析再动手。 在已有 checkpoint + 运行中代码库上做增量变更，不是从零开始。 每次变更都经过 G-E 收敛循环验证设计质量，再通过 RALPH 循环实现。
与 /implement 的关系
/implement = 从 checkpoint 出发，全量实现（Phase 0→1→2→3）
/change = 在已实现的项目上，增量变更（分析→设计→实现→回归）
/implement 建造房子
/change 改造房间
/change 复用 /implement 的全部基础设施（agents、hooks、rules、scripts）， 但增加了影响分析和增量设计两个前置阶段。
使用方式
# 完整流程（4 阶段）
/change 新增 whale alert：检测大额交易推送 webhook 通知
# 仅分析影响（不实现）
/change analyze 新增 whale alert 功能
# 从设计结果继续实现（已有 change-request）
/change implement CR-003
# 查看变更历史
/change log
# bug fix 快捷模式（跳过完整设计，但仍有影响分析）
/change fix 钱包初始化超时未重试
变更类型
| 类型 | 触发词 | 设计深度 | 示例 |
|---|---|---|---|
| feature | 新增、添加、支持 | 完整（4 阶段） | "新增 whale alert 功能" |
| enhance | 修改、优化、改进 | 中等（影响分析 + 增量设计） | "优化钱包初始化并发数" |
| refactor | 重构、拆分、合并 | 中等（影响分析 + 架构评审） | "拆分 ingestion 模块" |
| fix | 修复、bug、问题 | 轻量（影响分析 + 直接实现） | "修复扫链 reorg 处理" |
4 阶段流程
Stage A: ANALYZE（影响分析）
│ 主 session 执行，可与用户交互
│
│ 1. 读取变更描述 → 分类（feature/enhance/refactor/fix）
│ 2. 扫描现有 checkpoint-1~5 → 找到相关 FR、聚合、API、DDL
│ 3. 扫描现有代码库 → 找到受影响的文件和模块
│ 4. 检测新增环境依赖（新 infra / 新 API / 新 RPC）
│ 5. 生成影响报告 → 展示给用户确认
│
│ 产出：change-request-{N}.yaml（影响范围 + 变更计划 + 新增环境依赖）
│
Stage B: DESIGN（增量设计）
│ Agent(change-analyst) — G-E 收敛循环
│
│ 1. 根据变更类型，增量更新相关 checkpoint：
│ - feature → 追加 FR 到 checkpoint-1，可能更新 2/3/4
│ - enhance → 修改已有 FR，更新 checkpoint-4
│ - refactor → 更新 checkpoint-2/3，可能更新 4
│ - fix → 通常不更新 checkpoint（除非是设计缺陷）
│ 2. Generator 提出 checkpoint 变更 → Evaluator 评审一致性
│ 3. 用户确认 checkpoint 变更
│
│ 产出：更新后的 checkpoint 文件 + change-request 状态更新
│
──── 如果有新增环境依赖 → 环境询问（见下方） ────
Stage C: IMPLEMENT（增量实现）
│ 复用 impl-lead + RALPH 循环
│
│ 1. impl-lead 只处理 change-request 中的变更范围
│ 2. 如果需要新 DDL → impl-skeleton 执行增量迁移
│ 3. 如果需要新 verify scripts → impl-deploy 更新脚本
│ 4. RALPH 内层循环：RED → GREEN → REVIEW → DEPLOY → COMMIT
│ 5. 每个变更功能一个 commit（Conventional Commits）
│
│ commit 格式根据变更类型：
│ feature → feat({module}): {description}
│ enhance → feat({module}): {description}
│ refactor → refactor({module}): {description}
│ fix → fix({module}): {description}
│
Stage D: REGRESS（回归验证）
│ 主 session + impl-reviewer
│
│ 1. 全量测试（不仅仅是变更部分）
│ 2. 全量 smoke test
│ 3. impl-reviewer 对变更代码做独立评审
│ 4. 检查未被变更但被影响的模块是否仍通过
│ 5. 更新 change-request 状态 → completed
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.
- 2d ago First seen · 437 lines · 83 tokens per session scan A 6f0cb19fe06c
change is a command published in the GitHub repository infra403/agentic-engineering-lab (5 stars, last pushed 4mo ago), licensed MIT. It adds 83 tokens to every session and 3,988 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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.