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/implementgit 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 | $0.00078 | $0.04853 |
| Opus 5 | $0.00039 | $0.02426 |
| Sonnet 5 | $0.00016 | $0.00971 |
| Haiku 4.5 | $0.00008 | $0.00485 |
Grade C, and why
implement scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- `block-dangerous-commands.sh` — 阻止 `rm -rf`, `DROP TABLE` 等 How it starts
The opening of the file, as written. The whole thing — 419 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/implement 命令
核心理念
- 环境先声明 → deploy-manifest.yaml 是环境合约，tech-profile.yaml 是语言合约
- 完成一个功能就部署 → 不攒到最后
- LLM 输出不可信 → Hooks 自动验证，不靠人记得检查
- 部署失败可回滚 → 自动恢复上一个可用版本
- 语言无关 → 所有语言特定命令封装在 tech-profile.yaml
- RALPH 自动驱动 → Read→Analyze→List→Plan→Handle 外层循环，自动遍历所有功能直到全部完成
Claude Code 高级特性使用
| 特性 | 用途 |
|---|---|
| Agent frontmatter | 每个 agent 有独立的 tools, permissionMode, maxTurns, memory, hooks |
Git Worktree (isolation: worktree) |
impl-skeleton/acceptance/module/api/observe 在隔离 worktree 中并行工作 |
| Hooks (PreToolUse/PostToolUse/SubagentStop) | 自动格式化、阻止修改 checkpoint、RED/GREEN 验证 |
Path-Specific Rules (.claude/rules/) |
编码/SQL/API/事件/测试/部署规范按路径自动加载 |
| Permission Modes | Lead=plan（只调度）, 实现者=acceptEdits（自动批准编辑） |
| disallowedTools | acceptance 不能 spawn Agent, module 不能 spawn Agent |
| memory: project | agent 记住项目约定，跨 session 复用 |
| effort: high/max | Lead(opus, max), acceptance/module/entry(high) |
| SessionStart hook | compact 后自动重注入项目上下文 |
| Stop hook | 验证所有 task 完成后才允许停止 |
使用方式
/implement # 完整实施（4 阶段 ~24 tasks）
/implement declare # 仅 Phase 0
/implement infra # 仅 Phase 1
/implement feature <name> # 实施某功能
/implement deploy <name> # 部署某功能
/implement rollback # 回滚到上一版本
/implement from <N> # 从 Task N 继续
/implement status # 查看进度
/implement smoke # 全量冒烟
⛔ 启动前必须完成的用户询问（主 Session 执行）
关键设计约束：子 agent（impl-deploy, impl-lead 等）被 spawn 后无法与用户交互。 因此所有需要用户回答的问题必须在主 session 中、spawn agent 之前完成。 以下三个问题必须在命令启动后、spawn impl-lead 之前，由主 session 直接向用户提问。
询问 1：应用部署目标（deploy_target）
在做任何事之前，先问用户：
你的应用部署到哪里？
1. local — 本地开发运行（默认）
2. remote-ssh — SSH 到远程服务器部署
3. docker-remote — 远程服务器 docker-compose 部署
4. k8s — Kubernetes 集群部署
如果用户选 remote-ssh 或 docker-remote，追问：
请提供远程服务器信息：
- SSH 地址（如 [email protected]）
- SSH 端口（默认 22）
- 远程项目路径（如 /opt/polymarket-hub）
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 · 419 lines · 78 tokens per session scan C 5fd608391663
implement is a command published in the GitHub repository infra403/agentic-engineering-lab (5 stars, last pushed 4mo ago), licensed MIT. It adds 78 tokens to every session and 4,853 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
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.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.