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 opendatahub-io/ai-helpers --skill torchtalk-analyzergit clone --depth 1 https://github.com/opendatahub-io/ai-helpersWrote 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/opendatahub-io/ai-helpers/torchtalk-analyzer)<a href="https://agentmods.dev/skills/opendatahub-io/ai-helpers/torchtalk-analyzer"><img src="https://agentmods.dev/badge/skills/opendatahub-io/ai-helpers/torchtalk-analyzer/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/opendatahub-io/ai-helpers/torchtalk-analyzer"><img src="https://agentmods.dev/badge/skills/opendatahub-io/ai-helpers/torchtalk-analyzer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00058 | $0.01641 |
| Opus 5 | $0.00029 | $0.00821 |
| Sonnet 5 | $0.00012 | $0.00328 |
| Haiku 4.5 | $0.00006 | $0.00164 |
Grade A, and why
torchtalk-analyzer 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 8d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TorchTalk Analyzer
This skill enables cross-language analysis of PyTorch internals by leveraging the TorchTalk MCP server. It traces binding chains from Python through C++ to CUDA, analyzes dispatch mechanisms, maps call graphs, and locates test infrastructure.
When to Use
- When asked how a PyTorch operator works internally (e.g., "How does torch.add dispatch to CUDA?")
- When investigating where a function is implemented across CPU/CUDA/MPS backends
- When assessing what would break if a C++ function is modified (impact analysis)
- When tracing how torch.nn modules connect to native ATen operators
- When finding existing tests for a PyTorch operator or function
- When exploring PyTorch's dispatch architecture or autograd integration
Prerequisites
- TorchTalk MCP server must be running and registered with Claude Code
- PyTorch source code must be available locally
- Run
/torchtalk:setupif TorchTalk is not yet installed
Verify availability:
mcp__torchtalk__get_status
If the status tool returns data, all tools below are ready.
Instructions
Step 1 - Verify MCP Server
Before using any tools, confirm the TorchTalk server is running:
mcp__torchtalk__get_status
Check that:
- Bindings are loaded (should show thousands of bindings)
- Native functions are parsed
- C++ call graph status is "Ready" (required for impact/calls/called_by)
- Python modules are loaded (required for trace_module/list_modules)
If the server is not available, direct the user to run /torchtalk:setup.
Step 2 - Identify the Analysis Type
Match the user's question to the appropriate tool:
| Question Pattern | Tool | Example |
|---|---|---|
| "How does X work?" / "Trace X" | mcp__torchtalk__trace |
trace("softmax", "full") |
| "Find functions matching X" | mcp__torchtalk__search |
search("conv", "CUDA") |
| "Where are the CUDA kernels for X?" | mcp__torchtalk__cuda_kernels |
cuda_kernels("softmax") |
| "What does X call?" | mcp__torchtalk__calls |
calls("at::native::add") |
| "What calls X?" | mcp__torchtalk__called_by |
called_by("at::native::add") |
| "What breaks if I change X?" | mcp__torchtalk__impact |
impact("at::native::add", 3) |
| "How does nn.Linear work?" | mcp__torchtalk__trace_module |
trace_module("Linear") |
| "List all nn modules" | mcp__torchtalk__list_modules |
list_modules("nn") |
| "Find tests for X" | mcp__torchtalk__find_similar_tests |
find_similar_tests("softmax") |
| "What test utilities exist?" | mcp__torchtalk__list_test_utils |
list_test_utils("all") |
| "What tests are in file X?" | mcp__torchtalk__test_file_info |
test_file_info("test_torch") |
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.
- 8d ago First seen · 135 lines · 58 tokens per session scan A a69a2b2be0a9
torchtalk-analyzer is a skill published in the GitHub repository opendatahub-io/ai-helpers (37 stars, last pushed 4d ago), licensed Apache-2.0. It adds 58 tokens to every session and 1,641 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 2026-09-03.
Other skills, from other repositories
cuopt-numerical-optimization-api
LP, MILP, and QP (beta) with cuOpt — Python, C, and CLI. Use when the user is solving LP, MILP, or QP with any cuOpt interface.
ampl-python
Expert in amplpy and Python integration with AMPL. Use when writing or refactoring amplpy scripts, notebooks, FastAPI services, data pipelines (pandas/polars), solver configuration via Python, result extraction, or Colab/MO-Book Python workflows. Knows amplpy.ampl.com and dev.ampl.com amplpy best practices.
temporal-python-testing
Test Temporal workflows with pytest, time-skipping, and mocking strategies. Covers unit testing, integration testing, replay testing, and local development setup. Use when implementing Temporal workflow tests or debugging test failures.
fastapi-templates
Create production-ready FastAPI projects with async patterns, dependency injection, and comprehensive error handling. Use when building new FastAPI applications or setting up backend API projects.
manimgl-best-practices
Trigger when: (1) User mentions "manimgl" or "ManimGL" or "3b1b manim", (2) Code contains from manimlib import , (3) User runs manimgl CLI commands, (4) Working with InteractiveScene, self.frame, self.embed(), ShowCreation(), or ManimGL-specific patterns. Best practices for ManimGL (Grant Sanderson's 3Blue1Brown…
cuopt-developer
Modify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI). Use for solver internals, PRs, DCO, and code conventions.