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/modelstudioai/cli/stress-batch-testsgit clone --depth 1 https://github.com/modelstudioai/cliWhat 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 | $0.00000 | $0.03328 |
| Opus 5 | $0.00000 | $0.01664 |
| Sonnet 5 | $0.00000 | $0.00666 |
| Haiku 4.5 | $0.00000 | $0.00333 |
Grade A, and why
stress-batch-tests 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
批量压测脚本（多能力统一入口）
使用者文档（方案说明、命令示例、fixtures、默认值表）：../stress-testing.md
触发条件
- 新增、修改或排查
packages/cli/tests/stress/**/*.mjs批量压测代码 - 用户要求并发压测
bl各能力（文本 / 语音 / 图像 / 视频等）、生成 Markdown/HTML 报告 - 修改对应命令的 JSON 输出字段后，需同步
packages/cli/tests/stress/lib/parsers.mjs与各targets/*.mjs的成功判定 - 在 monorepo 根
package.json调整test:stress入口
不要为压测去改 CLI 产品行为（除非用户明确要求修 CLI bug）；压测侧通过子进程参数与解析逻辑适配现有命令。
与 E2E / vp test 的关系
| 维度 | E2E（Vitest） | 批量压测（.mjs） |
|---|---|---|
| 路径 | packages/cli/tests/e2e/*.e2e.test.ts |
packages/cli/tests/stress/run.mjs + targets/*.mjs、lib/*.mjs |
| 运行 | vp test（真实 API 需 BAILIAN_E2E=1） |
仅手动 pnpm run test:stress -- <target> -- ... |
| 目的 | 回归：help、缺参、dry-run、单条集成 | 并发、限流、耗时统计、批量报告、前置资源 fixtures |
| CI | 可纳入 vp test（skip 块默认跳过） |
禁止默认 CI / vp test 自动执行 |
vp test 只收集 *.test.ts / *.spec.ts 等，不会执行 tests/stress/*.mjs。勿将压测逻辑写成 Vitest 用例并放进默认测试流。
E2E 规范见 cli-e2e-tests.md。
文件与入口
packages/cli/tests/stress/
├── run.mjs # 路由入口（解析 target、全局 flags、`--`）
├── lib/
│ ├── argv-parse.mjs # 共用 --count/-n、-c、-m、--voice、--report-dir 等
│ ├── stress-config.mjs # count/concurrency 配置加载与解析
│ ├── cli-runner.mjs # spawn main.ts、限流重试、线程池
│ ├── fixtures.mjs # prerequisites.json + 前置音频/图/视频生成
│ ├── parsers.mjs # 各命令 stdout / 文件解析
│ ├── paths.mjs
│ ├── rate-limit.mjs
│ ├── finish-run.mjs # 写报告；套件模式返回摘要而不 exit
│ ├── run-suite.mjs # 全量套件编排
│ ├── suite-catalog.mjs # 用例顺序与中文名
│ ├── suite-report.mjs # SUITE_REPORT.md / .html
│ ├── trace-ids.mjs # requestId / taskId 提取
│ └── report.mjs # REPORT.md / REPORT.html / results.json
└── targets/
├── text-chat.mjs
├── speech-synthesize.mjs
├── speech-recognize.mjs
├── image-generate.mjs
├── image-edit.mjs
├── video-t2v.mjs
├── video-i2v.mjs
├── video-ref.mjs
└── video-edit.mjs
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 · 223 lines · 0 tokens per session scan A fe645cc2f8d3
stress-batch-tests is an agent published in the GitHub repository modelstudioai/cli (320 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 3,328 tokens. 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 2026-08-30.
Other agents, from other repositories
hildegard
Medieval polymath persona channeling Hildegard von Bingen — herbal medicine from Physica, holistic health from Causae et Curae, sacred music composition, viriditas philosophy, and natural history consultation.
interface-craft
Weight: 0.8 | Polish layer, context-dependent.
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.