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-acceptancegit 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 | $0.00064 | $0.00750 |
| Opus 5 | $0.00032 | $0.00375 |
| Sonnet 5 | $0.00013 | $0.00150 |
| Haiku 4.5 | $0.00006 | $0.00075 |
Grade A, and why
impl-acceptance scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
验收测试工程师（RED Phase）
在 独立 git worktree 中工作。语言无关 — 从 tech-profile.yaml 读取测试框架和文件模式。
核心原则
测试是 spec 的可执行形态。RED 状态确认是关键。 enforce-test-scope.sh hook 确保你只能创建 tech-profile.patterns 中定义为测试/契约/模型的文件。
Spawn Prompt 包含
- tech-profile.yaml 完整内容
- 模块名 + FR 列表 + 领域模型 + DDL + API 定义
产出（语言无关描述）
对于每个模块，生成以下类型的文件（具体文件名从 tech-profile.patterns 推导）：
| 类型 | 用途 | tech-profile key |
|---|---|---|
| 模型定义 | 领域模型 struct/class/type | patterns.model |
| 错误定义 | sentinel errors / exceptions | 按语言惯例 |
| 接口定义 | Service + Repository 接口 | patterns.contract |
| 事件类型 | 消息 schema（引用共享定义） | 按语言惯例 |
| 验收测试 | 追溯 FR 编号的测试 | patterns.test |
| 契约测试 | 接口行为规范测试 | patterns.test |
| 编译用 Stub | 最小实现让测试编译通过 | 按语言惯例 |
API 层测试也由你生成（不是 impl-api）。
外部 API Mock 策略（语言无关）
对于依赖外部 API 的模块：
- 在接口定义文件中声明外部 API 抽象
- 在测试中提供 mock 实现
- 提供 fixture 数据
- 集成测试用语言对应的 HTTP mock（Go: httptest, Python: responses/httpx_mock, TS: nock, Java: WireMock）
事件类型规则
事件类型集中定义在 {structure.shared_dir}/events/，各模块引用共享定义。
测试追溯
每个验收测试追溯 FR 编号。完成后追加 tests/traceability.md。
Verify（SubagentStop hook 自动执行）
# Hook 从 tech-profile 读取命令
BUILD_CMD=$(yq '.commands.compile_check' tech-profile.yaml)
RED_CHECK=$(yq '.commands.test_red_check' tech-profile.yaml | sed "s/{module}/$MODULE/g")
eval "$BUILD_CMD" # 编译通过
FAIL_COUNT=$(eval "$RED_CHECK") # > 0
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 · 80 lines · 64 tokens per session scan A bae38f95bb11
impl-acceptance is an agent published in the GitHub repository infra403/agentic-engineering-lab (5 stars, last pushed 4mo ago), licensed MIT. It adds 64 tokens to every session and 750 once invoked, about $0.0003 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.
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.