agentmods.dev

attnres: Instructions file for Claude Code

CLAUDE.md

attnres CLAUDE.md is an instructions file for Claude Code from AbdelStark/attnres. It costs 581 tokens per session, scanned A, original, MIT.

Repository instructions for a Rust machine-learning project that experiments with Transformer models and includes a WebAssembly web demo. They describe the project’s identity, status, layout, working rules, and checks.

In plain words
What is it for?
Understanding the repository structure, checking project status, following contribution rules, and running formatting, linting, tests, example builds, and the web-demo build.
Why use it?
They give an coding agent the project context and rules needed to work consistently, while recording which claims and validations are still unconfirmed.

Instructions file for Claude Code

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

This is AbdelStark/attnres's own configuration. It tells Claude Code how to work on attnres 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 attnres configures →

not rated 54repo 5mo ago A scan 581 tokens original MIT
View source ↗ AbdelStark/attnres abdelstark.github.io
Reuse

Borrowing it

Nothing to install: this file belongs to AbdelStark/attnres. 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/AbdelStark/attnres/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/AbdelStark/attnres

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 attnres CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/abdelstark/attnres/claude-md.svg)](https://agentmods.dev/instructions/abdelstark/attnres/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/abdelstark/attnres/claude-md"><img src="https://agentmods.dev/badge/instructions/abdelstark/attnres/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 581 This file is loaded in full into every session.
When invoked 581 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 $0.00581 $0.00581
Opus 5 $0.00291 $0.00291
Sonnet 5 $0.00116 $0.00116
Haiku 4.5 $0.00058 $0.00058

Measured 8d ago against content hash d93bc7ef2ed8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

attnres 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 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.

CLAUDE.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Identity

attnres is a Rust implementation of Attention Residuals for burn-based Transformer experiments. The repository includes a library crate, examples, benchmarks, and a separate WASM web demo.

Status

  • Alpha as of March 16, 2026.
  • Verified locally during the latest quality pass:
    • cargo fmt -- --check
    • cargo clippy -- -D warnings
    • cargo test --all-features
    • cargo build --examples
    • cd web-demo && npm run build
  • Not yet validated:
    • GPU backend correctness/performance claims
    • PyTorch checkpoint interchange
    • Stable 1.0 API guarantees

Repository Map

  • README.md: project front door and current status.
  • ARCHITECTURE.md: current architecture and invariants.
  • ROADMAP.md: milestones and known limitations.
  • CONTRIBUTING.md: contributor workflow and required checks.
  • CHANGELOG.md: user-visible changes.
  • src/config.rs: config validation and typed config errors.
  • src/model.rs: full model and two-phase forward entry points.
  • src/layer.rs: per-layer AttnRes logic and block-boundary handling.
  • src/attn_res_op.rs: core depth attention operator.
  • web-demo/: standalone WASM reimplementation plus Vite app.

Working Rules

  • Prefer try_validate / try_init_model when config is not hard-coded.
  • Algorithm changes must be backed by tests or paper-referenced reasoning.
  • Keep docs factual. Do not repeat stale test counts or unsupported capability claims.
  • Avoid touching Cargo.toml dependencies or .github/workflows/ without explicit approval.
  • There is no local spec.md in this checkout. Treat ARCHITECTURE.md, module docs, and tests as the current source of truth.

Critical Invariants

  • Pseudo-query vectors are zero-initialized.
  • Softmax is over depth, not over sequence positions.
  • Each Transformer layer has two AttnRes operations.
  • Block boundaries are defined in sublayer space.
  • The embedding block is always the first completed block.

Web Demo Design Context

Audience:

Read the full file on GitHub · 73 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. 8d ago First seen · 73 lines · 581 tokens per session scan A d93bc7ef2ed8

Subscribe to this mod's changes

attnres CLAUDE.md is an instructions file published in the GitHub repository AbdelStark/attnres (54 stars, last pushed 5mo ago), licensed MIT. It adds 581 tokens to every session, about $0.0029 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.

llm-inferencellm-trainingmachine-learningrust-machine-learning
Related

Other instructions, from other repositories

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

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

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

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 · 7,104 tokens