Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/rnixai/rnix/claude-mdgit clone --depth 1 https://github.com/rnixai/rnixWrote 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/rnixai/rnix/claude-md)<a href="https://agentmods.dev/instructions/rnixai/rnix/claude-md"><img src="https://agentmods.dev/badge/instructions/rnixai/rnix/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 | $0.13747 | $0.13747 |
| Opus 5 | $0.06874 | $0.06874 |
| Sonnet 5 | $0.02749 | $0.02749 |
| Haiku 4.5 | $0.01375 | $0.01375 |
Grade A, and why
rnix 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 4d 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 — 352 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
Rnix is an operating system for AI agents, inspired by Unix design philosophy. It provides process management, a virtual filesystem (VFS), IPC via Unix domain sockets, multi-agent orchestration, intent decomposition, and debugging tools. Written in Go 1.26, module github.com/rnixai/rnix.
Project Context
_bmad-output/project-context.md
Build & Development Commands
每次会话的编码工作完成后，要运行一次 make all 检查是否有错误需要修复。
make build # Build binary → ./rnix
make test # Run all tests with race detection
make lint # golangci-lint
make vet # go vet
make all # lint + vet + test + build
make agtest # Tier1 agent-behavior regression suite, isolated daemon (PR gate; not part of `all`)
make agtest-live # Tier2 advisory suite against your ambient daemon + real provider/API key
# Run a single test
go test -race -run TestFunctionName ./package/...
# Run tests for a specific package
go test -race ./kernel/...
go test -race ./ipc/...
Prerequisite: Go 1.26+ (managed via mise.toml).
Architecture
Daemon Model
Rnix runs as a background daemon holding the kernel and process table. CLI commands communicate with the daemon over a Unix domain socket ($XDG_RUNTIME_DIR/rnix/rnix.sock or /tmp/rnix-$UID/rnix.sock). The CLI auto-starts the daemon via EnsureDaemon() if not running. Manage the daemon with rnix daemon status and rnix daemon stop.
Core Data Flow
CLI (cmd/rnix) → IPC Client → Unix Socket → IPC Server → Kernel
↓
Process ReasonStep Loop
↓ ↑
VFS Devices Context
(LLM, FS, Shell, MCP)
Package Dependency Hierarchy
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.
- 4d ago First seen · 352 lines · 13,747 tokens per session scan A c23a29e8cb5d
rnix CLAUDE.md is an instructions file published in the GitHub repository rnixai/rnix (5 stars, last pushed 26d ago), licensed MIT. It adds 13,747 tokens to every session, about $0.0687 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 2026-08-31.
Other instructions, from other repositories
ollama AGENTS.md
AGENTS.md instructions for ollama/ollama, covering agents.md and building.
ollama CLAUDE.md
Claude Code instructions for ollama/ollama: See AGENTS.md for the shared agent instructions for this repository.
pipelex AGENTS.md
Instructions for Pipelex/pipelex, covering pipelex coding rules, codex cloud commands, linting, keyword-only arguments check and cleaning derived files.
pipelex CLAUDE.md
Instructions for Pipelex/pipelex, covering pipelex coding rules, commands, linting, keyword-only arguments check and cleaning derived files.
manifold AGENTS.md
Instructions for intelligencedev/manifold, covering go/manifold, coding conventions, project structure & module organization, package organization and dependency injection.
gollem CLAUDE.md
Instructions for gollem-dev/gollem, covering claude.md, restriction & rules, commands, development and testing and test execution.