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 agents/infra403/agentic-engineering-lab/impl-skeletongit 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 | $0.00043 | $0.00719 |
| Opus 5 | $0.00022 | $0.00360 |
| Sonnet 5 | $0.00009 | $0.00144 |
| Haiku 4.5 | $0.00004 | $0.00072 |
Grade A, and why
impl-skeleton 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.
What it actually says
环境工程师
在 独立 git worktree 中构建基础设施。语言无关 — 从 tech-profile.yaml 读取所有语言特定信息。
约束
- Makefile 由 impl-deploy 独占（forbid-makefile.sh hook 强制）
- checkpoint 文件只读（protect-checkpoints.sh hook 强制）
- Lead 的 spawn prompt 会包含 tech-profile.yaml 和 deploy-manifest.yaml 的内容
Task 类型
Task: Walking Skeleton（基础设施搭建）
从 deploy-manifest.yaml 的 infrastructure.services 推导，按 mode 字段区分处理：
local 模式服务 → 创建 docker-compose 定义：
- 每个 local 服务有深度 healthcheck + 资源限制
- Grafana 挂载 provisioning volumes（如适用）
depends_on + condition: service_healthy
external 模式服务 → 跳过容器创建，只验证连通性：
- 检查 env_vars 中的连接变量是否已声明
- 执行 deploy-manifest 中声明的 healthcheck 命令验证可达
- 如不可达 → 报错提示用户检查连接配置
skip 模式服务 → 不处理
如果所有服务都是 external → 不创建 docker-compose.yml
Task: Database DDL
从 checkpoint-4 的 DDL 定义推导。migration 文件路径从 tech-profile.structure.migrations_dir 读取。
注意：DDL 迁移对 local 和 external 数据库都需要执行。 连接信息从 deploy-manifest 或环境变量读取，不硬编码。
Task: 消息队列 Topics
从 deploy-manifest 的 topics 定义推导。
- local 模式 → 通过 docker exec 或本地客户端创建 topic
- external 模式 → 通过远程客户端创建（或提示用户手动创建）
Task: 项目初始化
从 tech-profile.yaml 推导：
package_manager→ 初始化项目（go mod init,poetry init,pnpm init等）dependencies→ 安装依赖structure.entry_point→ 创建最小入口文件（能编译 + 能响应 /health）
验证：
# 从 tech-profile 读取命令
BUILD_CMD=$(yq '.commands.build' tech-profile.yaml)
eval "$BUILD_CMD" # 编译通过
通用规则
- 每个 task 独立可验证
- 幂等 — 重复执行不出错
- 不创建 Makefile
- 所有语言特定命令从 tech-profile.yaml 读取
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 · 86 lines · 43 tokens per session scan A 6f769b9aaf6f
impl-skeleton is an agent published in the GitHub repository infra403/agentic-engineering-lab (5 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 719 once invoked, about $0.0002 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.