Borrowing it
Nothing to install: this file belongs to tensorcircuit/tensorcircuit-ng. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tensorcircuit/tensorcircuit-ng/master/.agents/skills/sanity-checker/SKILL.mdgit clone --depth 1 https://github.com/tensorcircuit/tensorcircuit-ngWrote 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/tensorcircuit/tensorcircuit-ng/sanity-checker)<a href="https://agentmods.dev/skills/tensorcircuit/tensorcircuit-ng/sanity-checker"><img src="https://agentmods.dev/badge/skills/tensorcircuit/tensorcircuit-ng/sanity-checker.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00061 | $0.01403 |
| Opus 5 | $0.00030 | $0.00701 |
| Sonnet 5 | $0.00012 | $0.00281 |
| Haiku 4.5 | $0.00006 | $0.00140 |
Grade A, and why
sanity-checker 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 7d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When activated, you act as a Senior Systems Architect and Code Quality Auditor. Your mission is to systematically identify and reduce technical debt and "entropy" within the TensorCircuit-NG codebase. You prioritize structural integrity, clean abstractions, and maintainable patterns over quick fixes.
1. Audit Scope & Workflow
- Scope: If a path is provided, focus the audit there. If no path is specified, you MUST scan the entire codebase (
tensorcircuit/,tests/andexamples/directories). You can use the provided reference scripts in.agents/skills/sanity-checker/reference/as starting points for automated static analysis. - Report-First: Your primary output is a Sanity Check Report. You MUST NOT modify any files until the USER has reviewed and explicitly approved the report.
- Action: After approval, you will perform the refactoring in a surgical manner, ensuring each change is verified.
2. Dependency & Import Management
- Optional Dependencies: Identify imports of optional TensorCircuit dependencies (e.g.,
qiskit,pennylane,cupy,tensorflow,torch,jax). These MUST be imported within the function or method scope where they are used to prevent mandatory installation requirements for users. - Required & First-Party Dependencies: Ensure all core dependencies and first-party
tensorcircuitimports are located at the top of the file. Inexamples/, every dependency should be imported at the top of the file.
3. Documentation & Comments
- Cruft Removal: Identify and mark for removal any comments that are:
- Outdated: No longer reflecting the current code logic.
- Verbose/Unnecessary: Explaining the "obvious" or providing AI-generated "chain-of-thought" (e.g., "I will now calculate X because...").
- "Thinking Loudly": Personal notes or speculative comments that don't add value to the production codebase.
- Public API Docstrings: Every public class and method MUST have a well-documented docstring. Verify that:
- They are up-to-date with the implementation.
- They include clear descriptions of all parameters and return types.
- Docstring Formatting: After the opening
""", start the docstring content on a new line unless the entire docstring consists of a single line.
What ships with it
2 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.
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.
- 7d ago First seen · 65 lines · 61 tokens per session scan A 16e62fe8051b
sanity-checker is a skill published in the GitHub repository tensorcircuit/tensorcircuit-ng (89 stars, last pushed 6d ago), licensed Apache-2.0. It adds 61 tokens to every session and 1,403 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
physicsnemo-shard-tensor
Official NVIDIA-authored guidance for PhysicsNeMo ShardTensor domain parallelism — integrate domain parallelism into training/inference scripts (new or existing) with DDP or FSDP2, write and register shard patches to enable new layers/ops, and bootstrap multi-GPU correctness tests. Use when working with ShardTensor…
physicsnemo-discover
Official NVIDIA-authored guidance for navigating PhysicsNeMo — pick the model, datapipe, or example for a SciML/AI4Science task (surrogates, forecasting, downscaling, physics-informed, inverse, generative). Points at existing files via live repo search; never writes code. Do NOT use for installation or environment…
code-review
Perform comprehensive code reviews focusing on best practices, security vulnerabilities, performance optimization, and maintainability.
retentioneering-contributing
Help the user turn their Retentioneering ideas, friction reports, bug findings, or feature needs into high-quality upstream contributions: from capturing and validating the idea, through minimal reproductions and issue drafts, to preparing, testing, and submitting a pull request that follows this repository's…
fine-tuning-serving-openpi
Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference across ALOHA, DROID, and LIBERO environments. Use when adapting pi0 models to custom datasets, converting JAX checkpoints to PyTorch, running policy inference servers, or debugging…
ml-engineering
Field-tested methodology and concrete recipes for training and operating large-scale LLM/VLM/multi-modal models end to end - choosing and benchmarking accelerators, storage and network; SLURM/Kubernetes orchestration; maximizing training throughput and fitting models in memory; diagnosing and surviving training…