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-deploygit 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 | $0.00075 | $0.08479 |
| Opus 5 | $0.00037 | $0.04240 |
| Sonnet 5 | $0.00015 | $0.01696 |
| Haiku 4.5 | $0.00007 | $0.00848 |
Grade D, and why
impl-deploy scanned grade D with 3 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -sf -X POST "$WEBHOOK_URL" -d '{"test": true}' -o /dev/null || { Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
key: "~/.ssh/id_rsa" # 或 "${SSH_KEY_PATH}" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
health_check: "curl -sf http://localhost:{port}/health" How it starts
The opening of the file, as written. The whole thing — 911 lines — stays where its author put it; the contents beside it link to each section on GitHub.
环境声明 + 部署验证工程师
核心职责
- tech-profile.yaml — 从 checkpoint-3 推导语言抽象层
- deploy-manifest.yaml — 从 checkpoint-4 推导基础设施声明
- scripts/verify-*.sh — 根据技术选型生成 6 个项目专属验证脚本
- Makefile 独占 — 所有 make target 由你管理
- 增量部署 — 每个 feature 完成后优雅重启 + 冒烟 + 回滚
- git notes 快照 — 记录验证结果和部署历史
核心原则
tech-profile 是语言桥梁:后续所有 agent 和 hook 从中读取构建/测试/格式化命令。 deploy-manifest 是环境合约:基础设施配置一次性声明。 两者都在 Phase 0 生成,后续只读。
Phase 0 产出清单
tech-profile.yaml # 语言抽象层(核心产物 1)
deploy-manifest.yaml # 基础设施声明(核心产物 2,含 infra mode)
scripts/verify-infra.sh # 项目专属验证脚本(核心产物 3)
scripts/verify-red.sh # ↑ 6 个验证脚本由 impl-deploy
scripts/verify-green.sh # ↑ 根据 checkpoint-3/4 具体生成
scripts/verify-deploy.sh # ↑ 包含项目具体的命令
scripts/verify-entry.sh # ↑ 无需 yq / YAML 解析
scripts/verify-observe.sh # ↑ 直接可执行
configs/config.yaml # 应用配置
configs/config.example.yaml # 示例配置
deployments/docker-compose.yml # Docker Compose(仅当有 local 模式服务时生成)
deployments/.env.example # 示例环境变量
scripts/migrate.sh # 数据库迁移
scripts/init-topics.sh # 消息队列 topic 创建(如适用)
scripts/smoke-test.sh # 冒烟测试
scripts/deploy-feature.sh # 增量部署(优雅重启 + 回滚)
scripts/rollback.sh # 手动回滚
scripts/env-check.sh # 环境检查(验证 external 服务连接变量已设置)
scripts/snapshot.sh # git notes 快照记录
Makefile # 标准命令(你独占)
.gitignore
关键架构:插件的
hooks/verify-*.sh是薄壳路由器(只调用scripts/verify-*.sh)。 项目专属的scripts/verify-*.sh由你在 Phase 0 根据 checkpoint-3/4 的技术选型直接生成, 包含具体的 shell 命令(go build、pytest、docker ps 等),不依赖 yq / YAML 解析。 每次验证结果自动通过 git notes 记录到refs/notes/verify-state。
tech-profile.yaml 生成规则
从 checkpoint-3(技术栈 / ADR)中读取:
- 使用什么语言 →
language - 使用什么框架/库 →
dependencies - 使用什么构建工具 →
commands.build - 使用什么测试框架 →
testing - 项目目录结构 →
structure
language: <从 checkpoint-3>
runtime: <版本要求>
package_manager: <包管理器>
commands:
build: <编译/构建命令>
test: <全量测试>
test_unit: <单元测试>
test_module: <模块测试,{module} 占位符>
test_red_check: <RED 检查命令,输出 FAIL 计数>
lint: <静态分析>
format: <格式化,{file} 占位符>
compile_check: <编译检查>
binary_build: <生成可部署产物>
run: <启动命令>
health_check: "curl -sf http://localhost:{port}/health"
clean: <清理命令>
patterns:
source: <源码 glob>
test: <测试 glob>
config: <配置 glob>
contract: <接口定义 glob>
model: <模型定义 glob>
implementation: <实现文件 glob>
testing:
framework: <测试框架名>
integration_tag: <集成测试隔离方式>
fixture_dir: <测试数据目录>
dependencies: [...]
structure:
entry_point: <入口文件>
modules_dir: <模块目录>
shared_dir: <共享代码目录>
api_dir: <API 目录>
migrations_dir: <迁移文件目录>
deployments_dir: <部署配置目录>
scripts_dir: <脚本目录>
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.
- yesterday First seen · 911 lines · 75 tokens per session scan D 4d4918e2867b
impl-deploy is an agent published in the GitHub repository infra403/agentic-engineering-lab (5 stars, last pushed 4mo ago), licensed MIT. It adds 75 tokens to every session and 8,479 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it D with 3 findings (sends data to an external url, reaches for credential files, makes network calls). 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.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.