Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/infra403/agentic-engineering-labnpx agentmods add agents/infra403/agentic-engineering-lab/impl-deployWrote 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.
[](https://agentmods.dev/agents/infra403/agentic-engineering-lab/impl-deploy)<a href="https://agentmods.dev/agents/infra403/agentic-engineering-lab/impl-deploy"><img src="https://agentmods.dev/badge/agents/infra403/agentic-engineering-lab/impl-deploy/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.
<a href="https://agentmods.dev/agents/infra403/agentic-engineering-lab/impl-deploy"><img src="https://agentmods.dev/badge/agents/infra403/agentic-engineering-lab/impl-deploy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00075 | $0.08479 |
| Opus 5.5 | $0.00030 | $0.03392 |
| Sonnet 5.5 | $0.00015 | $0.01696 |
| Haiku 4.5 | $0.00007 | $0.00848 |
Grade D, and why
impl-deploy scanned grade D with 3 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -sf -X POST "$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.
- 1mo ago 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 5mo ago), licensed MIT. It adds 75 tokens to every session and 8,479 once invoked, about $0.0003 per session on Opus 5.5. 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
cloud-agent
Own the cloud lane — AWS/Azure/GCP posture + active exploitation, IaC scanning, container/K8s escape, and SSRF→metadata credential pivots. Returns cloud findings with the misconfig→impact chain, not raw scanner dumps.
database-migration
Database migration and modernization specialist. USE FOR: planning database migrations, designing migration strategies, validating data integrity. DO NOT USE FOR: operational database management, routine backups.
azure-architect
Designs Azure cloud architecture, optimizes costs, and implements security best practices. Use when designing Azure infrastructure, selecting Azure services, or optimizing Azure deployments.
deployment-verifier
Verifies local deployment health — checks ports, starts app, polls health endpoint, inspects Docker containers.
grumpy-budget-hawk
Cloud cost reviewer. Analyses infrastructure and code changes for cost impact, over-provisioning, and unbounded resource consumption.
aws-principal-architect
Provide expert AWS Principal Architect guidance using AWS Well-Architected Framework principles and AWS best practices.