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.
git clone --depth 1 https://github.com/ck3938700-ship-it/anjian-agentWrote 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/commands/ck3938700-ship-it/anjian-agent/audit-web)<a href="https://agentmods.dev/commands/ck3938700-ship-it/anjian-agent/audit-web"><img src="https://agentmods.dev/badge/commands/ck3938700-ship-it/anjian-agent/audit-web/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/commands/ck3938700-ship-it/anjian-agent/audit-web"><img src="https://agentmods.dev/badge/commands/ck3938700-ship-it/anjian-agent/audit-web.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 | $0.00000 | $0.00138 |
| Opus 5 | $0.00000 | $0.00069 |
| Sonnet 5 | $0.00000 | $0.00028 |
| Haiku 4.5 | $0.00000 | $0.00014 |
Grade A, and why
audit-web scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
请使用 anjian MCP 工具处理这个网站安全评估请求：$ARGUMENTS
在任何网络操作前，必须向我确认并收集：资产所有者或授权身份、书面授权依据、授权结束日期、明确允许端口，以及是否允许内网地址。如果缺少任何一项，只提问，不运行检查。
默认运行 baseline。自动结果一律作为 observation；没有人工复现理由时不得标记为 confirmed。生成中文 Markdown 和 HTML 报告，并写明未执行工具、评估范围与限制。active 模式只能提示我去终端亲自解锁，不能代替我解锁。
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.
- 10d ago First seen · 6 lines · 0 tokens per session scan A d7cb996d38e8
audit-web is a command published in the GitHub repository ck3938700-ship-it/anjian-agent (0 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 138 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 2026-08-31.
Other commands, from other repositories
toefl-grade
A TOEFL answer-scoring command that uses a local language model, and speech-to-text software for recordings, to assess reading, listening, writing, and speaking practice. TOEFL is an English test with separate reading, listening, writing, and speaking sections.
toefl-practice
A local, offline generator for TOEFL practice questions. TOEFL is an English-language test with reading, listening, speaking, and writing sections.
toefl-roadmap
A weekly TOEFL study planner that reads your personal schedule and shows the relevant week, today's tasks, and the exam countdown.
toefl-status
A read-only command that summarizes progress toward a TOEFL exam, an English-language test. It reads a schedule, study journal, and score history to show the countdown, progress, score trends, gaps, and weak areas.
toefl-drill
A TOEFL practice routine that finds your weakest question types and creates repeated exercises for them. TOEFL is an English test covering reading, listening, speaking and writing.
opencode
Manage OpenCode/Zen connections, switch models, and configure local Ollama.