What is torchtalk CLAUDE.md?

Project instructions for Torchtalk, an MCP server that analyzes how Python and C++ code connects inside PyTorch.

They help inspect Python modules, C++ call graphs, and native bindings, then query the indexed PyTorch source through MCP tools.

They give developers the commands and architecture needed to install, test, lint, and run the analysis server correctly.

How TorchedHat/torchtalk configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to TorchedHat/torchtalk. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/TorchedHat/torchtalk/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/TorchedHat/torchtalk

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/torchedhat/torchtalk/claude-md/github.svg)](https://agentmods.dev/instructions/torchedhat/torchtalk/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/torchedhat/torchtalk/claude-md"><img src="https://agentmods.dev/badge/instructions/torchedhat/torchtalk/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/torchedhat/torchtalk/claude-md"><img src="https://agentmods.dev/badge/instructions/torchedhat/torchtalk/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 197 This file is loaded in full into every session.

When invoked 197 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00197	$0.00197
Opus 5.5	$0.00079	$0.00079
Sonnet 5.5	$0.00039	$0.00039
Haiku 4.5	$0.00020	$0.00020

Measured 1mo ago against content hash ceb7d5f4d371, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

torchtalk CLAUDE.md 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 1mo 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.

CLAUDE.md · 14 lines

What it actually says

@AGENTS.md

Claude Code

The MCP tools are exposed as mcp__torchtalk__get_status, mcp__torchtalk__trace, mcp__torchtalk__search, mcp__torchtalk__graph, mcp__torchtalk__modules, mcp__torchtalk__tests and mcp__torchtalk__affected. Call them directly; never import or run torchtalk.server from Python.
.mcp.json registers the server for this checkout. .claude-plugin/plugin.json and hooks/hooks.json package it as a plugin, and scripts/plugin-setup.sh installs it on session start.
/trace <name> (in .claude/commands/) and the torchtalk-analyzer skill (in .claude/skills/) wrap the common workflows.

Changes

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.

1mo ago Changed · -96 lines · -1,008 tokens per session ceb7d5f4d371
2mo ago First seen · 110 lines · 1,205 tokens per session scan A 10f357d69c3a

Subscribe to this mod's changes

torchtalk CLAUDE.md is an instructions file published in the GitHub repository TorchedHat/torchtalk (12 stars, last pushed 28d ago), licensed MIT. It adds 197 tokens to every session, about $0.0008 per session on Opus 5.5. 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.

torchtalk CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
torchtalk CLAUDE.mdTorchedHat/torchtalk	Instructions file	12	28d ago	MIT	A	197	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

torchtalk: Instructions file for Claude Code