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 skills add qualcomm/qai-appbuilder --skill qai-runner-skillgit clone --depth 1 https://github.com/qualcomm/qai-appbuilderWrote 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/qualcomm/qai-appbuilder/qai-runner-skill)<a href="https://agentmods.dev/skills/qualcomm/qai-appbuilder/qai-runner-skill"><img src="https://agentmods.dev/badge/skills/qualcomm/qai-appbuilder/qai-runner-skill/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/skills/qualcomm/qai-appbuilder/qai-runner-skill"><img src="https://agentmods.dev/badge/skills/qualcomm/qai-appbuilder/qai-runner-skill.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 | $0.00108 | $0.04969 |
| Opus 5 | $0.00054 | $0.02485 |
| Sonnet 5 | $0.00022 | $0.00994 |
| Haiku 4.5 | $0.00011 | $0.00497 |
Grade A, and why
aipc-toolkit scanned grade A with 1 finding 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 9d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- Python scripts via `subprocess.run()` — no shell quoting issues The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
41 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/aipc_AGENTS.md 40 KB
- assets/aipc_plan.md 83 KB
- README.md 9.9 KB
- references/accuracy_checking.md 27 KB
- references/evolve.md 8.8 KB
- references/host_context_binary_gen.md 15 KB
- references/inference.md 28 KB
- references/model_export_validation.md 11 KB
- references/model_quantization_aimet.md 7.0 KB
- references/model_quantization.md 3.0 KB
- references/model_split.md 29 KB
- references/multi_component_pipeline.md 22 KB
- references/on_device_context_binary.md 7.8 KB
- references/operator_patching.md 43 KB
- references/optimization.md 4.9 KB
- references/profiling.md 13 KB
- references/qnn_conversion.md 13 KB
- references/snpe_conversion.md 2.1 KB
- references/troubleshooting_quick.md 4.9 KB
- references/troubleshooting.md 18 KB
- scripts/aipc 3.0 KB
- scripts/aipc_convert_aimet.py 10 KB runs code
- scripts/aipc_convert_fp.py 21 KB runs code
- scripts/aipc_convert_int.py 22 KB runs code
- scripts/aipc_convert_snpe.py 7.6 KB runs code
- scripts/aipc_dev_gen_contextbin_x86.py 6.3 KB runs code
- scripts/aipc_dev_gen_contextbin.py 5.8 KB runs code
- scripts/aipc_inspect_onnxio.py 4.2 KB runs code
- scripts/aipc_preflight_check.py 5.9 KB runs code
- scripts/aipc_project_setup.py 9.6 KB runs code
- scripts/aipc_qairt_devinfo.ps1 9.9 KB runs code
- scripts/convert_qnn_to_trace.py 5.3 KB runs code
- scripts/onnxwrapper_x86.py 14 KB runs code
- scripts/onnxwrapper.py 96 KB runs code
- setup/ubuntu/qaiappbuilder_linux_install_sop.md 4.0 KB
- setup/ubuntu/QAIRT_SETUP_SOP_linux.md 5.7 KB
- setup/ubuntu/README.md 2.5 KB
- setup/win_installer/PythonShell.bat 2.7 KB runs code
- setup/win_installer/scripts/install_vs.ps1 9.3 KB runs code
- setup/win_installer/scripts/setup_qairt_env.py 19 KB runs code
- setup/win_installer/Setup_Env.bat 19 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.
- 9d ago First seen · 322 lines · 108 tokens per session scan A 2c84f165a7c4
aipc-toolkit is a skill published in the GitHub repository qualcomm/qai-appbuilder (219 stars, last pushed today), with no licence file. It adds 108 tokens to every session and 4,969 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
spark-environment-setup
Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.
spark-memory-thermal-ops
Manage unified memory and thermals during long-running ML jobs on NVIDIA DGX Spark. Use when planning memory headroom for a training run on GB10, when a job OOMs on unified memory, or when monitoring temperature and power during multi-hour training.
spark-training-gotchas
Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.
llama-cpp
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.
amc-run-rtsp-calibration
Calibrate a new dataset from live RTSP camera streams via the AutoMagicCalib REST API. Use when the user provides RTSP URLs or asks to calibrate live cameras; VIOS records clips, AMC ingests them, then runs calibration.
amc-run-video-calibration
Calibrates pre-recorded cam.mp4 datasets through the AutoMagicCalib REST API. Use for user-supplied local MP4s; route live RTSP streams to amc-run-rtsp-calibration.