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 skills/autozyx-labs/adsafetypilot/dfm-querynpx skills add AutoZYX-Labs/ADSafetyPilot --skill dfm-querygit clone --depth 1 https://github.com/AutoZYX-Labs/ADSafetyPilotWrote 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/skills/autozyx-labs/adsafetypilot/dfm-query)<a href="https://agentmods.dev/skills/autozyx-labs/adsafetypilot/dfm-query"><img src="https://agentmods.dev/badge/skills/autozyx-labs/adsafetypilot/dfm-query.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 | $0.00035 | $0.00912 |
| Opus 5 | $0.00017 | $0.00456 |
| Sonnet 5 | $0.00007 | $0.00182 |
| Haiku 4.5 | $0.00003 | $0.00091 |
Grade A, and why
dfm-query 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 5d 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
DFM 查询 | Driver Foundation Model Query
本技能基于驭研科技(DRIVEResearch)750h+航测自然驾驶数据集,提供中国驾驶员在特定场景下的行为参数分布基线。
概念
驾驶员基础模型(DFM)回答五个核心问题:
- How: 人类在这个场景下怎么开?→ 参考轨迹
- What: 合理范围是什么?→ 能力包络(P5-P95)
- Where: 哪里需要格外注意?→ 热点区域
- When: 什么触发了行为变化?→ 触发条件
- Why: 人类在意哪些信息?→ 关键环境线索
数据来源
- 采集方式:无人机航测(上帝视角,无遮挡)
- 数据规模:750h+ 飞行时数,10.5M+ 轨迹片段
- 覆盖范围:高速公路、城市道路、匝道、弯道、环岛、施工区、停车场、冰雪路面
- 数据网站:https://www.driveresearch.tech/
可查询参数
| 参数 | 说明 | 单位 |
|---|---|---|
| TTC | 碰撞时间 | s |
| THW | 车头时距 | s |
| DHW | 车头间距 | m |
| Lat_Acc | 横向加速度 | m/s^2 |
| Lon_Acc | 纵向加速度 | m/s^2 |
| Jerk | 加加速度 | m/s^3 |
| Speed | 车速 | km/h |
| Rel_Speed | 相对速度 | km/h |
| Lane_Offset | 车道偏移 | m |
输出格式
每个查询返回百分位值分布:
{
"scenario": "highway_cut_in",
"matched_trajectories": 12847,
"parameters": {
"TTC": {"P5": 2.8, "P25": 4.1, "P50": 6.5, "P75": 10.2, "P95": 18.7, "unit": "s"},
"THW": {"P5": 0.87, "P25": 1.21, "P50": 1.62, "P75": 2.15, "P95": 3.41, "unit": "s"},
"Rel_Speed": {"P5": -35.2, "P25": -22.1, "P50": -15.3, "P75": -8.7, "P95": -2.1, "unit": "km/h"}
},
"sotif_notes": "P5 THW=0.87s significantly below ISO 22179 threshold of 1.2s"
}
状态
⚠️ Phase 2 — 数据注入准备中
当前为框架定义阶段。DRIVEResearch数据预计算完成后,将注入20个核心场景的行为基线数据。
使用示例
用户:高速公路匝道合流场景,主路车速100km/h,查询中国驾驶员行为基线
输出:
场景匹配: Highway Merge (JAMA Annex C Type-2)
匹配轨迹数: N(待注入)
行为基线: TTC/THW/加速度 P5-P95分布
SOTIF建议: 基于P5极端值的安全阈值建议
与CCDM/RSS对比: 中国数据 vs 欧洲数据差异
参考文献
- Zhang, Y., Wang, C., & Shum, H. (2026). Benchmarking Autonomous Vehicles: A Driver Foundation Model Framework. CARS 2026.
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.
- 5d ago First seen · 77 lines · 35 tokens per session scan A 12b190ec0363
dfm-query is a skill published in the GitHub repository AutoZYX-Labs/ADSafetyPilot (2 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 912 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…