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 ascend-ai-coding/awesome-ascend-skills --skill inference-precision-tensor-dump-comparegit clone --depth 1 https://github.com/ascend-ai-coding/awesome-ascend-skillsWrote 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/ascend-ai-coding/awesome-ascend-skills/inference-precision-tensor-dump-compare)<a href="https://agentmods.dev/skills/ascend-ai-coding/awesome-ascend-skills/inference-precision-tensor-dump-compare"><img src="https://agentmods.dev/badge/skills/ascend-ai-coding/awesome-ascend-skills/inference-precision-tensor-dump-compare/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/ascend-ai-coding/awesome-ascend-skills/inference-precision-tensor-dump-compare"><img src="https://agentmods.dev/badge/skills/ascend-ai-coding/awesome-ascend-skills/inference-precision-tensor-dump-compare.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 | $0.00087 | $0.03784 |
| Opus 5 | $0.00044 | $0.01892 |
| Sonnet 5 | $0.00017 | $0.00757 |
| Haiku 4.5 | $0.00009 | $0.00378 |
Grade A, and why
inference-precision-tensor-dump-compare 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
9 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.
- references/checklist.md 9.9 KB
- references/framework-integration.md 23 KB
- references/review-guide.md 14 KB
- references/tensor-tags-guide.md 8.7 KB
- references/verification-debugging.md 11 KB
- scripts/analyze_logs.py 12 KB runs code
- scripts/inject_tensor_dump.py 47 KB runs code
- scripts/rollback_tensor_dump.py 8.2 KB runs code
- scripts/verify_tags.py 3.4 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.
- 5d ago First seen · 351 lines · 87 tokens per session scan A 5eff1f88e366
inference-precision-tensor-dump-compare is a skill published in the GitHub repository ascend-ai-coding/awesome-ascend-skills (167 stars, last pushed yesterday), with no licence file. It adds 87 tokens to every session and 3,784 once invoked, about $0.0004 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 2026-09-05.
Other skills, from other repositories
memory_leak
Detect monotonic GPU memory growth across training steps.
training_hang
Training stalled — capture stacks and thread/blocking hints.
vllm-ascend-tuning
A guide to tuning vLLM-Ascend, a system for running language models on Ascend hardware. It covers standalone use, pipeline use, and quantization tuning, which reduces model precision to change performance or resource use.
sglang
Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.
miles-rl-training
Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring speculative RL for maximum throughput.
debug-inference
Debug why inference.local, direct external inference, or supervisor-only system inference is failing. Use when the user cannot reach a local model server, has provider base URL issues, sees inference verification failures, hits protocol mismatches, or needs to diagnose inference on local vs remote gateways. Trigger…