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 commands/qingzhoupro/afsim-skill/afsim-autogit clone --depth 1 https://github.com/qingzhoupro/afsim-skillWrote 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/qingzhoupro/afsim-skill/afsim-auto)<a href="https://agentmods.dev/commands/qingzhoupro/afsim-skill/afsim-auto"><img src="https://agentmods.dev/badge/commands/qingzhoupro/afsim-skill/afsim-auto.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 | $0.00000 | $0.01327 |
| Opus 5 | $0.00000 | $0.00664 |
| Sonnet 5 | $0.00000 | $0.00265 |
| Haiku 4.5 | $0.00000 | $0.00133 |
Grade A, and why
afsim-auto 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 3d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/afsim-auto — AFSIM 代码自动生成
两种模式
全自动（/afsim-auto <需求>）
接收需求 → 自动解析 → 找模板 → 生成 → 自检 → 输出。全流程无需确认。
半自动（/afsim-auto step <需求>）
每次只生成一个模块，每步等待确认后再继续。适合新手学习或复杂场景。
全自动模式流程
Step 0: 需求理解
解析用户描述，提取关键要素：
- 平台类型（飞机/舰船/地面/导弹）
- 阵营（红方/蓝方/绿方）
- 是否带传感器、武器、处理器
- 仿真时长
- 特殊功能（行为树、路由、雷达等）
需求模糊时，全自动模式会尝试推断并补充默认值，必要时在输出后提示用户确认。
Step 1: 加载模板
按需求类型加载对应模板：
| 需求类型 | 模板来源 |
|---|---|
| 飞机平台 | refs/quick-ref.md 最小原型 + templates/ |
| 舰船/地面 | refs/demos-index.md 找 launcher/ship demo |
| 带传感器 | refs/demos-index.md 找 sensor demo |
| 带武器 | refs/demos-index.md 找 weapon/engage demo |
| 复杂逻辑 | refs/demos-index.md 找 processor/script demo |
Step 2: 代码生成
基于模板修正输出，遵循：
- 不凭空自造语法
- 块结构完整（所有
end_*存在） - 基类型正确（
WSF_PLATFORM、WSF_AIR_MOVER等） - 参数格式正确（坐标 d:m:s、时间单位、速度单位）
Step 3: 自检
生成后自动检查：
- 所有
end_*闭合完整 - 基类型拼写正确
- 参数格式正确
- 单位正确（ft、kts、m 等）
- 无行尾注释
Step 4: 输出到 staging
将生成的代码写入文件到 output/staging/，不直接输出代码块：
文件路径：output/staging/<场景名称>.txt
文件内容：[生成的 AFSIM 代码]
同时告知用户：
- 输出路径
- 内容摘要（包含哪些 platform_type、sensor、weapon 等）
- 下一步操作（用 Warlock 打开验证）
Step 5: 归档闭环
用户认可后（或 Warlock 验证通过），将文件移动到 output/verified/ 对应子目录：
mv output/staging/<name>.txt output/verified/scenario/
mv output/staging/<name>.txt output/verified/component/
mv output/staging/<name>.txt output/verified/template/
在目标目录的 README 中追加元信息（来源、日期、功能描述）。
半自动模式流程（step）
逐模块构建清单
Task Progress:
- [ ] Step 1: 需求确认
- [ ] Step 2: 基础平台定义（platform_type + platform）
- [ ] Step 3: 传感器（如有）
- [ ] Step 4: 武器（如有）
- [ ] Step 5: 处理器/脚本逻辑（如有）
- [ ] Step 6: 路路由与阵位
- [ ] Step 7: 全局配置（random_seed, end_time, log_file）
- [ ] Step 8: 自检确认
Step 1: 需求确认
解析用户需求，输出需求摘要，等待确认：
我将为你构建以下 AFSIM 场景：
- 红方 SAM 系统 vs 蓝方战机
- 包含：LAUNCHER_TYPE（platform_type）、FINDER_SENSOR、TIR_SENSOR、LRSAM_WEAPON、TRACK_PROCESSOR
- 仿真时长：50 min
确认请回复 "是" 或补充信息。
Step 2-7: 逐模块生成
每个模块生成后等待确认：
【Step 2/8】基础平台定义
platform_type LAUNCHER_TYPE WSF_PLATFORM
side red
icon SA-10_Launcher
weapon lrsam LRSAM
quantity 1
end_weapon
end_platform_type
platform launcher1 LAUNCHER_TYPE
side red
position 40:00:00n 116:00:00e altitude 0 ft msl
end_platform
确认以上平台定义？[是/修改/跳过]
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.
- 3d ago First seen · 160 lines · 0 tokens per session scan A 65e92a29e2e7
afsim-auto is a command published in the GitHub repository qingzhoupro/afsim-skill (51 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,327 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 2026-08-30.
Other commands, from other repositories
training
Build the training plan for today (or a given date).
check-dev
Type-check a Z specification with fuzz.
me-figure-discussion
Write or review thermal-fluid figure discussion with observation, physical mechanism, comparison, uncertainty, and claim limits.
master_analysis
Run comprehensive 5-phase analysis across labs, genetics, and protocols.
run-panguweather
Guide the user through running PanguWeather end-to-end on an AMD cluster.
render-figures
Compile all .tex and .typ figure files in a directory.