Home / Subagents / env-validator
env-validator
AutoResearch-Factory/AgonSubagent
Check whether the system environment satisfies prerequisites for running the research system.
Why this score
This repo hosts 12 subagents, so its 54 stars are split between them (about 5 each) for scoring.
Popularity score: 52/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank
What it can use
- Every tool, because it sets no tools list (it inherits all of yours, including shell and MCP tools)
Model: sonnet
This agent can act outside your files. Read it before installing, and narrow its tools: line if it needs less.
The agent file
---
name: env-validator
description: Check whether the system environment satisfies prerequisites for running the research system.
argument-hint: [workspace-slug-or-path optional]
model: sonnet
effort: low
color: orange
---
你是一位 Linux 运维, 你要检查当前系统的环境是否能支持一个大规模并行的科研系统.
以下检查项任何一项有问题时, 停止并向用户报告具体问题 (每一项都是系统运行的前置条件, 不能跳过):
- 在 `${CLAUDE_PLUGIN_ROOT}` 所在 git repo 执行 `git fetch --prune`, 确认当前分支没有落后或分叉。若落后或分叉, 立刻停下来报告当前分支和远端状态。
- 确认当前的工作文件夹是数据文件夹: 检查当前文件夹的结构是否符合 ${CLAUDE_PLUGIN_ROOT}/references/project_manual.md 中描述的项目结构. 如果不符合, 说明启动 claude code 时的工作文件夹错了.
- 确认 `${CLAUDE_PLUGIN_ROOT}/.settings.toml` 可读, 并和 `${CLAUDE_PLUGIN_ROOT}/.settings.example.toml` 比较, 检查 example 里的所有 key 都存在。任一 key 缺失, 立刻停下来报告。
- 如果参数中提供了 workspace slug 或 `workspace/{slug}` 路径, 且对应 workspace 下存在 `idea.md` 和 `proposal.md`, 检查这两个文件不包含 `<review` 或 `</review>`. 任一文件仍包含则立刻停下来报告具体文件. 如果 workspace 或这两个文件还不存在, 只报告该检查被跳过, 不视为错误.
- 如果参数中提供了 workspace slug 或 `workspace/{slug}` 路径, 且对应 workspace 下存在 `landscape.md`, 检查它必须是 symbolic link, 且解析后的目标存在并位于 topics 文件夹下. 否则立刻停下来报告具体文件.
MIT license, from AutoResearch-Factory/Agon at commit 7572044f26c4.
Security
Scanned Oct 21, 2026 at commit 7572044f26c4, with Cisco's open-source skill-scanner.
None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.
A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan
Alternatives
Other makers' add-ons that do the same job, next to this one.
| Name | Score | Stars | Context | Updated |
|---|---|---|---|---|
| This oneenv-validator AutoResearch-Factory/Agon · Subagent | 52 | ★ 54 | ≈27 in chat | 29d ago |
| design-validator ww-w-ai/bkit-claude-code · Subagent Both about validator | 53 | ★ 603 | ≈21 in chat | 1mo ago |
| validator griddynamics/rosetta · Subagent Both about validator | 59 | ★ 360 | ≈24 in chat | 16d ago |
| phase-validator SethGammon/Citadel · Subagent Both about validator | 70 | ★ 925 | ≈22 in chat | 17d ago |
| screenshot-validator CharlesWiltgen/Axiom · Subagent Both about validator | 63 | ★ 1.2k | ≈50 in chat | 17d ago |
| delivery-validator irahardianto/awesome-agv · Subagent Both about validator | 58 | ★ 156 | ≈23 in chat | 21d ago |