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/autoresearch-factory/agon/env-validatorgit clone --depth 1 https://github.com/AutoResearch-Factory/AgonWrote 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/autoresearch-factory/agon/env-validator)<a href="https://agentmods.dev/agents/autoresearch-factory/agon/env-validator"><img src="https://agentmods.dev/badge/agents/autoresearch-factory/agon/env-validator.svg" alt="Measured on agentmods" 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 | $0.00016 | $0.00443 |
| Opus 5 | $0.00008 | $0.00221 |
| Sonnet 5 | $0.00003 | $0.00089 |
| Haiku 4.5 | $0.00002 | $0.00044 |
Grade A, and why
env-validator 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 4d 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
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.
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.
- 4d ago First seen · 23 lines · 16 tokens per session scan A 7ef4d09cb87e
env-validator is an agent published in the GitHub repository AutoResearch-Factory/Agon (45 stars, last pushed 10d ago), licensed MIT. It adds 16 tokens to every session and 443 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
research-manager
Coordinate an auditable Researcher AI project from hypothesis through artifact review while enforcing execution and disclosure gates.
sibyl-light
Sibyl Research System lightweight agent. Used for quick evaluation tasks: debate roles (optimist, skeptic, strategist), section critique, and cross-critique.
sibyl-heavy
Sibyl Research System heavy-reasoning agent. Used for deep analysis tasks: synthesis, supervision, editing, critical review, and reflection.
sibyl-standard
Sibyl Research System standard agent. Used for literature research, planning, experiment design, and idea generation.
ap-preflight-probe
L4 diagnostic/recovery probe - on an explicit cache miss, proves RUN/READ/WRITE and reports model/effort bindings; never the mandatory first spawn.
accessibility-specialist
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.