What is VibeCodeHPC CLAUDE.md?

A framework for coordinating several command-line AI agents on shared optimization tasks. It can run on laptops, Linux systems, and high-performance computing systems.

Building multi-agent workflows, including high-performance-computing auto-tuning, agent communication, monitoring, and support for multiple AI command-line tools.

Managing many agents, their messages, directories, budgets, and health checks by hand is difficult. The project defines a common structure for coordinating them through terminal sessions and remote connections.

How Katagiri-Hoshino-Lab/VibeCodeHPC configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Katagiri-Hoshino-Lab/VibeCodeHPC. 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/Katagiri-Hoshino-Lab/VibeCodeHPC/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Katagiri-Hoshino-Lab/VibeCodeHPC

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/katagiri-hoshino-lab/vibecodehpc/claude-md/github.svg)](https://agentmods.dev/instructions/katagiri-hoshino-lab/vibecodehpc/claude-md)

Your own site

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

Per session 1,693 This file is loaded in full into every session.

When invoked 1,693 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	$0.01693	$0.01693
Opus 5	$0.00847	$0.00847
Sonnet 5	$0.00339	$0.00339
Haiku 4.5	$0.00169	$0.00169

Measured 11d ago against content hash 7b7005983234, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

VibeCodeHPC 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 11d 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 · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

VibeCodeHPC

Multi-CLI Multi-Agent Auto-Tuning Framework.

Project Overview

General-purpose multi-agent orchestration framework. HPC optimization is one workflow — pluggable strategies support any auto-tuning task.

Language Priority

Python → TypeScript (port) → Shell (minimal wrappers)

Design Principles

No external orchestration framework (no CrewAI/AutoGen/LangGraph)
Agent directory isolation without git worktree
Use each CLI's native multi-agent capabilities directly
No hardcoded paths — must run on WSL/macOS/Linux/supercomputers
tmux-based IPC
Unified TUI display

Package Structure

vibecodehpc/
├── adapters/     # CLI adapters (8 CLIs supported, see docs/cli_support_matrix.md)
│   └── base.py   # CLIAdapter ABC
├── registry.py   # AgentRegistry (JSONL-backed)
├── tmux_utils.py # tmux session/pane management
├── agent_manager.py # spawn/message/health
├── hooks/        # CLI-agnostic hook intents
└── monitor/      # periodic_monitor, periodic_enter

Component Classification

Core: tmux communication, registry, hooks, ChangeLog+SOTA, budget, SSH/HPC integration
Role: PM, SE, PG, CD (experimental), SOLO (alternative)
Skill: Optimization templates, parallelization, sub-agent, report generation
Workflow: Multi-agent auto-tuning, optimization cycle, evolutionary exploration

Reference Resources

../VibeCodeHPC-jp/ — Original implementation (read-only)
../3rd-party-repos/VibeCodeHPC_iWAPT/ — Paper and figures
../3rd-party-repos/openclaw/ — Skills/extension reference
dev/ — Development docs (ARCHITECTURE, REQUIREMENTS, CLI_METADATA, TODO, etc.)

Available Tools

python3 -m vibecodehpc setup — create tmux sessions and agent panes
python3 -m vibecodehpc send <agent> "msg" — inter-agent messaging
python3 -m vibecodehpc status / health — agent status check
vibecodehpc/monitor/periodic_monitor.py — background context/budget monitoring
vibecodehpc/monitor/periodic_enter.py — auto-send Enter to prevent IPC message stall
Agent-shared/skills/*/scripts/*.py — analytics tools (budget, SOTA, changelog, context)

Read the full file on GitHub · 141 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.

11d ago First seen · 141 lines · 1,693 tokens per session scan A 7b7005983234

Subscribe to this mod's changes

VibeCodeHPC CLAUDE.md is an instructions file published in the GitHub repository Katagiri-Hoshino-Lab/VibeCodeHPC (39 stars, last pushed 5mo ago), licensed MIT. It adds 1,693 tokens to every session, about $0.0085 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.

Building agents Claude Code Scientific auto-tuning hpc multiagent opencode tmux

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

VibeCodeHPC: Instructions file for Claude Code