nanochat-rs-ternary: Instructions file for Claude Code

CLAUDE.md

nanochat-rs-ternary CLAUDE.md is an instructions file for Claude Code from architehc/nanochat-rs-ternary. It costs 9,883 tokens per session, scanned A, original, MIT.

Project instructions for Claude Code describing a Rust implementation of a ternary machine-learning system. Ternary weights use three values, and a Cargo workspace is Rust’s way to organize several related crates in one project.

In plain words
What is it for?
Use them to create the Rust workspace, build the ternary core, and later implement CPU and GPU kernels according to the planned test gates.
Why use it?
They set the required repository layout, implementation order, hardware target, and tests that must pass before the next phase begins.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is architehc/nanochat-rs-ternary's own configuration. It tells Claude Code how to work on nanochat-rs-ternary itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything nanochat-rs-ternary configures →

Reuse

Borrowing it

Nothing to install: this file belongs to architehc/nanochat-rs-ternary. 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/architehc/nanochat-rs-ternary/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/architehc/nanochat-rs-ternary

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.

agentmods badge for nanochat-rs-ternary CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/architehc/nanochat-rs-ternary/claude-md/github.svg)](https://agentmods.dev/instructions/architehc/nanochat-rs-ternary/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/architehc/nanochat-rs-ternary/claude-md"><img src="https://agentmods.dev/badge/instructions/architehc/nanochat-rs-ternary/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.

agentmods 80×15 button for nanochat-rs-ternary CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/architehc/nanochat-rs-ternary/claude-md"><img src="https://agentmods.dev/badge/instructions/architehc/nanochat-rs-ternary/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 9,883 This file is loaded in full into every session.
When invoked 9,883 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.09883 $0.09883
Opus 5 $0.04942 $0.04942
Sonnet 5 $0.01977 $0.01977
Haiku 4.5 $0.00988 $0.00988

Measured 12d ago against content hash e41222aa8f9a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

nanochat-rs-ternary 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 12d 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 · 995 lines

How it starts

The opening of the file, as written. The whole thing — 995 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — nanochat-rs Ternary + mHC-lite Implementation Plan

For Claude Code. Execute phases in order. Each phase has a test gate — do not proceed to the next phase until the gate passes. All code lives in a Cargo workspace rooted at nanochat-rs-ternary/. Hardware target: dual AMD EPYC 9654 (224T, 1TB DDR5) + NVIDIA RTX PRO 6000 Blackwell (96GB).


Repository Layout (create first)

nanochat-rs-ternary/
├── Cargo.toml                    # workspace root
├── CLAUDE.md                     # this file
├── crates/
│   ├── ternary-core/             # Phase 1: packing, planar SoA, GGUF
│   │   ├── Cargo.toml
│   │   └── src/
│   │       ├── lib.rs
│   │       ├── encode.rs         # BitNet encoding (11=-1)
│   │       ├── pack.rs           # pack/unpack, group quantization
│   │       ├── planar.rs         # PlanarWeights: SoA layout, aligned alloc
│   │       ├── gguf.rs           # GGUF reader/writer for ternary types
│   │       └── verify.rs         # Triangle of Truth (Rust side)
│   │
│   ├── ternary-kernels/          # Phase 2: CPU + GPU compute kernels
│   │   ├── Cargo.toml
│   │   ├── build.rs              # cc::Build for C kernels, cuda compilation
│   │   ├── csrc/
│   │   │   ├── ternary_gemv.c    # adapted from ternary_final.c (v3.3.1)
│   │   │   ├── ternary_gemv.h    # C API header
│   │   │   └── ternary_dp4a.cu   # GPU decode kernel
│   │   └── src/
│   │       ├── lib.rs
│   │       ├── cpu.rs            # safe Rust wrappers over C FFI
│   │       ├── gpu.rs            # CUDA kernel launch wrappers
│   │       └── dispatch.rs       # runtime CPU feature detection + dispatch
│   │
│   ├── mhc-lite/                 # Phase 3: mHC-lite residual connections
│   │   ├── Cargo.toml
│   │   └── src/
│   │       ├── lib.rs
│   │       ├── n2.rs             # MhcLiteN2 (1 param, identity ↔ swap)
│   │       ├── n4.rs             # MhcLiteN4 (24 perms, full BvN)
│   │       ├── verify.rs         # doubly stochastic checks, composite gain
│   │       └── io.rs             # binary serialization (matches Python export)
│   │
│   ├── nanochat-model/           # Phase 4: transformer architecture
│   │   ├── Cargo.toml
│   │   └── src/
│   │       ├── lib.rs
│   │       ├── config.rs         # model configs (d20, 7B, 25B-MoE, 80B-MoE)
│   │       ├── embed.rs          # token + position embeddings
│   │       ├── norm.rs           # RMSNorm
│   │       ├── attention.rs      # MHA / GQA / MLA (with DeltaNet option)
│   │       ├── ffn.rs            # SwiGLU FFN (with MoE option)
│   │       ├── bitlinear.rs      # BitLinear: ternary GEMV dispatch
│   │       ├── block.rs          # TransformerBlock with mHC wiring
│   │       └── model.rs          # full model: embed → blocks → head
│   │
│   └── nanochat-serve/           # Phase 6: inference server
│       ├── Cargo.toml
│       └── src/
│           ├── main.rs           # CLI + Axum HTTP server
│           ├── engine.rs         # KV-cache, sampling, batched decode
│           └── api.rs            # OpenAI-compatible /v1/chat/completions
│
├── training/                     # Phase 5: PyTorch training
│   ├── mhc_lite.py              # mHC-lite module (BvN, exact DS)
│   ├── ternary_qat.py           # BitLinear STE, absmean quantization
│   ├── model.py                 # nanochat architecture in PyTorch
│   ├── train.py                 # training loop (Muon+Lion, WSD schedule)
│   ├── export.py                # PyTorch → GGUF + mHC binary export
│   └── requirements.txt
│
├── tests/                        # Integration tests
│   ├── triangle_of_truth.rs     # cross-validate all kernel paths
│   ├── mhc_property_tests.rs    # doubly stochastic invariants
│   ├── roundtrip_test.rs        # pack → GGUF → load → GEMV → verify
│   └── e2e_generate.rs          # full model forward pass sanity
│
└── benches/
    ├── gemv_bench.rs            # criterion benchmarks for all kernel paths
    └── mhc_overhead.rs          # verify mHC adds <0.001% overhead

Read the full file on GitHub · 995 lines

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.

  1. 12d ago First seen · 995 lines · 9,883 tokens per session scan A e41222aa8f9a

Subscribe to this mod's changes

nanochat-rs-ternary CLAUDE.md is an instructions file published in the GitHub repository architehc/nanochat-rs-ternary (22 stars, last pushed 1mo ago), licensed MIT. It adds 9,883 tokens to every session, about $0.0494 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.

Related

Other instructions, from other repositories

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,126 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens