AGENTS.md@evalsA
AGENTS.md@evals from tencentcloudbase/cloudbase-ai-toolkit is an AGENTS.md file: the standing instructions coding agents read in that repo.
mdr add tencentcloudbase/cloudbase-ai-toolkit/evals/AGENTS.md@git:20260928.b71829cPins git:20260928.b71829c in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 14 of 14 checks passed
- Kind
- AGENTS.md file
- Repository
- tencentcloudbase/cloudbase-ai-toolkit
- Path
evals/AGENTS.md- Versions recorded
- 1
- Latest version
- git:20260928.b71829c, committed Sep 28, 2026
- Size
- 1,204 bytes
- Repository stars
- 1,141
- License
- MIT
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# evals/ 子目录约定 - 本目录是 CloudBase Evals：面向 AI agent 的开源平台评测（对标 supabase/evals 形态）。设计背景与阶段性方案在评测仓库的 `specs/`（不入库），本目录只放对外内容。 - `evals/benchmark/` 是公开榜单场景；`evals/regression/` 追踪已知失败模式，不进公开榜单。 - 场景格式：每个场景一个目录，`PROMPT.md`（frontmatter：stage / interface（必填）/ product / topic）+ `EVAL.ts`（评分器）+ 可选 `README.md`。 - 评分器以确定性断言为主（真实状态回读），LLM judge 只做语义判断；静态正则只做客观二元判断。 - 编写场景前必须先核对 CloudBase 官方文档（API 签名、包名、端口、参数），不要凭记忆假设。 - runner 类型在 `packages/core`。`EVAL.ts` 仍是 scorer 草案，干跑用假上下文，不创建云环境。根 tsconfig 未 include 本目录，不会影响主构建。 - 进榜 experiment 必须有 `-no-skills` 孪生（见 `experiments/presets.ts`）。CLI 版本写在各 harness 的 `defaultCliVersion`。 - 榜单统计规范见 README：3-run 平均、harness 版本 pin、一次运行独占一个环境。
Read the whole file at its exact version.
How to install
mdr add tencentcloudbase/cloudbase-ai-toolkit/evals/AGENTS.md@sha256:7d1dccfb78ffbe1dThe line at the top of this page pins the label git:20260928.b71829c, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_mtd4yplhxlxh5cvr)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Sep 28, 2026.
Audit of the latest version
- pass: Size between 200 bytes and 200 KB (1204 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
tencentcloudbase/cloudbase-ai-toolkit · 1,141 stars · license MIT · pushed 2026-10-20 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_mtd4yplhxlxh5cvr GET https://markdownregistry.com/api/v1/resolve?ref=tencentcloudbase/cloudbase-ai-toolkit/evals/AGENTS.md GET https://markdownregistry.com/api/v1/blob/7d1dccfb78ffbe1d46206e00756ce86fbfeb3d562eb62f915b507b8683230b70
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: how to write a good AGENTS.md · AGENTS.md vs CLAUDE.md · which agent file does what.
More from tencentcloudbase/cloudbase-ai-toolkit
Every file in tencentcloudbase/cloudbase-ai-toolkit