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/tencent/yolo-master/agentnpx skills add Tencent/YOLO-Master --skill agentgit clone --depth 1 https://github.com/Tencent/YOLO-MasterWhat 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 | $0.00060 | $0.05568 |
| Opus 5 | $0.00030 | $0.02784 |
| Sonnet 5 | $0.00012 | $0.01114 |
| Haiku 4.5 | $0.00006 | $0.00557 |
Grade A, and why
yolo-master-agent 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.
The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/autotrain_cases.json 35 KB
- assets/autotrain_cases/01_yolo_benchmark.json 733 B
- assets/autotrain_cases/02_yolo_export.json 696 B
- assets/autotrain_cases/03_yolo_lora_train.json 1.5 KB
- assets/autotrain_cases/04_yolo_model_inspect.json 751 B
- assets/autotrain_cases/05_yolo_moe_diagnose.json 728 B
- assets/autotrain_cases/06_yolo_moe_prune.json 738 B
- assets/autotrain_cases/07_yolo_multimodal_evaluate.json 3.7 KB
- assets/autotrain_cases/08_yolo_multimodal_infer.json 14 KB
- assets/autotrain_cases/09_yolo_pipeline_experiment.json 1.9 KB
- assets/autotrain_cases/10_yolo_predict.json 2.9 KB
- assets/autotrain_cases/11_yolo_solutions_run.json 669 B
- assets/autotrain_cases/12_yolo_system.json 2.6 KB
- assets/autotrain_cases/13_yolo_track.json 904 B
- assets/autotrain_cases/14_yolo_train.json 3.0 KB
- assets/autotrain_cases/15_yolo_tune.json 631 B
- assets/autotrain_cases/16_yolo_ui_launch.json 499 B
- assets/autotrain_cases/17_yolo_val.json 1.6 KB
- assets/autotrain_cases/18_yolo_lora_diagnose.json 780 B
- assets/autotrain_cases/19_yolo_eval_peft_compare.json 1.2 KB
- assets/autotrain_cases/20_stability_check.json 7.0 KB
- assets/autotrain_cases/21_yolo_eval_sparse_sahi_compare.json 736 B
- assets/autotrain_cases/21_yolo_release_audit.json 506 B
- assets/autotrain_cases/22_yolo_job.json 1.1 KB
- assets/mini-detect/images/train/bus.jpg 134 KB
- assets/mini-detect/images/val/bus.jpg 134 KB
- assets/mini-detect/labels/train/bus.txt 38 B
- assets/mini-detect/labels/val/bus.txt 38 B
- assets/mini-detect/mini_detect.yaml 83 B
- assets/open_world_label_aliases.json 603 B
- assets/open-world-taxonomy/lvis_1203_classes.json 74 KB
- assets/open-world-taxonomy/lvis_1203_classes.txt 19 KB
- assets/open-world-taxonomy/sources.json 780 B
- assets/open-world-taxonomy/v3det_13204_classes.json 814 KB
- assets/open-world-taxonomy/v3det_13204_classes.txt 206 KB
- assets/prompts/vlm_coco_multitask.md 3.9 KB
- assets/prompts/vlm_open_world_caption_misses_compact.md 1.4 KB
- assets/prompts/vlm_open_world_detect_classify_compact.md 1.6 KB
- assets/prompts/vlm_open_world_detection_compact.md 1.7 KB
- assets/prompts/vlm_open_world_detection.md 4.0 KB
- metadata/openai.yaml 3.1 KB
- README.md 7.5 KB
- references/skill-architecture.md 43 KB
- references/thinking-with-image.md 9.1 KB
- runtime/__init__.py 60 B runs code
- runtime/cli/__init__.py 73 B runs code
- runtime/cli/async_jobs.py 5.4 KB runs code
- runtime/cli/compare_open_world_profiles.py 9.5 KB runs code
- runtime/cli/contract.py 13 KB runs code
- runtime/cli/core_handlers.py 26 KB runs code
- runtime/cli/dataset.py 9.6 KB runs code
- runtime/cli/device.py 11 KB runs code
- runtime/cli/dispatcher.py 13 KB runs code
- runtime/cli/executor.py 17 KB runs code
- runtime/cli/job_handlers.py 1.3 KB runs code
- runtime/cli/launcher_handlers.py 6.0 KB runs code
- runtime/cli/lora_tools.py 8.0 KB runs code
- runtime/cli/model_handlers.py 1.8 KB runs code
- runtime/cli/moe_tools.py 9.0 KB runs code
- runtime/cli/multimodal_handlers.py 50 KB runs code
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 · 312 lines · 60 tokens per session scan A 0a54e64e33ed
yolo-master-agent is a skill published in the GitHub repository Tencent/YOLO-Master (696 stars, last pushed 4d ago), licensed AGPL-3.0. It adds 60 tokens to every session and 5,568 once invoked, about $0.0003 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 skills, from other repositories
yolo-pipeline
YOLO detection, segmentation, classification, and pose estimation setup, training workflow, evaluation metrics, and XAI verification.
perf-torch-cuda-graphs
Apply CUDA Graphs to PyTorch workloads — API selection (torch.compile, PyTorch makegraphedcallables, TE makegraphedcallables, MCore CudaGraphManager, FullCudaGraphWrapper, manual torch.cuda.graph), code compatibility, capture workflows, dynamic pattern handling, and troubleshooting. Triggers: CUDA graph…
tao-train-grounding-dino
Grounding DINO for open-set object detection. Combines DINO-style detection with a BERT text encoder for language-guided detection — detects objects described by text prompts without a fixed class vocabulary. Use when training, evaluating, exporting, quantizing, or running inference for a TAO Grounding DINO model.…
tao-train-bevfusion
BEVFusion for multi-sensor 3D object detection. Fuses LiDAR point clouds and camera images in bird's-eye-view (BEV) space, used in autonomous driving for robust 3D perception. Use when training, evaluating, or running inference for a TAO BEVFusion model. Trigger phrases include "train BEVFusion", "LiDAR + camera…
tao-train-deformable-detr
Deformable DETR for 2D object detection. Uses deformable attention for efficient multi-scale feature processing, lighter than DINO with competitive accuracy. Use when training, evaluating, exporting, quantizing, or running inference for a TAO Deformable-DETR model. Trigger phrases include "train deformable-detr"…
ml-for-aec
Computer vision for buildings, image-to-floorplan, generative ML models, performance prediction, structural analysis ML, energy prediction, natural language to design, and point cloud ML for AEC computational design.