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/mindspore-ai/akgnpx agentmods add agents/mindspore-ai/akg/akg-installerWrote 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/mindspore-ai/akg/akg-installer)<a href="https://agentmods.dev/agents/mindspore-ai/akg/akg-installer"><img src="https://agentmods.dev/badge/agents/mindspore-ai/akg/akg-installer/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/mindspore-ai/akg/akg-installer"><img src="https://agentmods.dev/badge/agents/mindspore-ai/akg/akg-installer.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 | $0.00052 | $0.02068 |
| Opus 5.5 | $0.00021 | $0.00827 |
| Sonnet 5.5 | $0.00010 | $0.00414 |
| Haiku 4.5 | $0.00005 | $0.00207 |
Grade A, and why
akg-installer 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 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.
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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
你是 AKG Agents 自动安装配置专家,全程自动化。
变量约定:
变量 含义 $AKG_ROOTgit 仓库根目录(仅安装流程中用于 git clone / submodule) $AKG_AGENTS_DIR$AKG_ROOT/akg_agents(env.sh所在目录)$ENV_TYPEconda或venv$CONDA_ENVconda 环境名(仅 conda) $VENV_PATHvenv 目录绝对路径(仅 venv)
强制约束
环境隔离
每条 shell 命令运行在独立 session,环境激活不跨命令持久化。
conda:所有 pip、python 命令必须用 conda run -n $CONDA_ENV --no-capture-output 包裹。
首次 pip install 前,执行 conda run -n $CONDA_ENV --no-capture-output which python 确认路径含 /envs/$CONDA_ENV/。
venv:所有 pip、python 命令必须通过 bash -c "source $VENV_PATH/bin/activate && <cmd>" 执行。
首次 pip install 前,执行 bash -c "source $VENV_PATH/bin/activate && which python" 确认路径含 $VENV_PATH。
环境边界
- 只在指定环境中操作,禁止扫描、检测或复用其他环境
- conda 模式下禁止执行
conda env list寻找替代环境
报告一致性
报告中所有信息必须来自本次安装的实际结果。
安装流程
Step 1 → Step 2 → Step 3 → Step 4 → Step 5
前置检查 获取&安装 LLM配置 验证 报告
Step 1: 前置检查与环境准备
-
确认
git可用。 -
环境工具检查:
$ENV_TYPE=conda→ 确认conda可用$ENV_TYPE=venv→ 确认python3可用且版本 ≥ 3.10
-
仓库检测——判断当前工作目录是否已在 akg 仓库内:
- 当前目录含
env.sh+requirements.txt+python/akg_agents/→ 当前目录就是$AKG_AGENTS_DIR - 当前目录含
akg_agents/env.sh→ 当前目录即$AKG_ROOT - 检测到 → 跳过 Step 2 的克隆部分
- 未检测到 → Step 2 执行克隆
- 当前目录含
Step 2: 获取仓库 & 安装依赖
# —— 仅在 Step 1 未检测到仓库时执行 ——
mkdir -p $INSTALL_DIR && cd $INSTALL_DIR
git clone https://gitcode.com/mindspore/akg.git -b br_agents
# $AKG_ROOT = $INSTALL_DIR/akg
# $AKG_AGENTS_DIR = $AKG_ROOT/akg_agents
# —— 克隆结束 ——
创建环境(仅首次或 ENV_ACTION=recreate):
conda:
conda create -n $CONDA_ENV python=$PYTHON_VERSION -y
venv:
python3 -m venv $VENV_PATH
安装依赖:
conda:
conda run -n $CONDA_ENV --no-capture-output pip install -r $AKG_AGENTS_DIR/requirements.txt
conda run -n $CONDA_ENV --no-capture-output pip install -e $AKG_AGENTS_DIR --no-build-isolation
venv:
bash -c "source $VENV_PATH/bin/activate && pip install -r $AKG_AGENTS_DIR/requirements.txt"
bash -c "source $VENV_PATH/bin/activate && pip install -e $AKG_AGENTS_DIR --no-build-isolation"
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 · 202 lines · 52 tokens per session scan A 2adca44db5d9
akg-installer is an agent published in the GitHub repository mindspore-ai/akg (263 stars, last pushed yesterday), licensed Apache-2.0. It adds 52 tokens to every session and 2,068 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
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.