Borrowing it
Nothing to install: this file belongs to bjia56/cosmotop. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bjia56/cosmotop/main/CLAUDE.mdgit clone --depth 1 https://github.com/bjia56/cosmotopWrote 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/instructions/bjia56/cosmotop/claude-md)<a href="https://agentmods.dev/instructions/bjia56/cosmotop/claude-md"><img src="https://agentmods.dev/badge/instructions/bjia56/cosmotop/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01309 | $0.01309 |
| Opus 5 | $0.00655 | $0.00655 |
| Sonnet 5 | $0.00262 | $0.00262 |
| Haiku 4.5 | $0.00131 | $0.00131 |
Grade A, and why
cosmotop 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 9d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
cosmotop is a cross-platform system monitoring tool built as a single executable using Cosmopolitan Libc. It's a fork of btop++ that displays real-time system metrics (CPU, memory, disk, network, GPU, NPU) in a terminal interface. The project uses the Actually Portable Executable (APE) format to create binaries that run natively on multiple operating systems.
Build System and Commands
Core Build Commands
The project uses CMake with two distinct build targets that must be built separately:
# Build the multiplatform host executable (requires cosmocc toolchain)
export CC=cosmocc
export CXX=cosmoc++
cmake -B build-cosmotop -DTARGET=host
cmake --build build-cosmotop
# Build platform-native plugin binaries
cmake -B build-plugin -DTARGET=plugin
cmake --build build-plugin
Available Build Targets
TARGET=host: Builds the multiplatformcosmotop.comexecutable using Cosmopolitan LibcTARGET=plugin: Builds platform-specific plugin executables/DLLs for system data collection
Testing and Validation
No automated test suite is present. Manual testing involves:
- Running the built executable on target platforms
- Verifying system metrics collection functionality
- Testing GPU/NPU detection and monitoring capabilities
Architecture Overview
Dual-Binary Architecture
The project uses a unique dual-binary architecture:
-
Host Executable (
cosmotop.com): Multiplatform binary built with Cosmopolitan Libc that handles:- Terminal UI rendering and user interaction
- Generic system metrics processing
- Plugin management and communication
- Configuration and theme management
-
Platform Plugins: Native executables/DLLs for each supported OS that handle:
- OS-specific system data collection
- Hardware-specific metrics (GPU, NPU, sensors)
- Communication with host via plugin interface
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.
- 9d ago First seen · 129 lines · 1,309 tokens per session scan A c785a8a43049
cosmotop CLAUDE.md is an instructions file published in the GitHub repository bjia56/cosmotop (72 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 1,309 tokens to every session, about $0.0065 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.
Other instructions, from other repositories
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.
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.
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).
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).
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.
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.