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/nervsystems/llm9p/claude-mdgit clone --depth 1 https://github.com/NERVsystems/llm9pWrote 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/nervsystems/llm9p/claude-md)<a href="https://agentmods.dev/instructions/nervsystems/llm9p/claude-md"><img src="https://agentmods.dev/badge/instructions/nervsystems/llm9p/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 | $0.02810 | $0.02810 |
| Opus 5 | $0.01405 | $0.01405 |
| Sonnet 5 | $0.00562 | $0.00562 |
| Haiku 4.5 | $0.00281 | $0.00281 |
Grade A, and why
llm9p 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 5d 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 — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.
llm9p - Development Guide
This guide is for Claude Code and developers working on the llm9p codebase.
Quick Reference
Build and Run
# Build
go build -o llm9p ./cmd/llm9p
# Run with Anthropic API
ANTHROPIC_API_KEY=sk-... ./llm9p -addr :5640
# Run with Claude Max subscription (via CLI)
./llm9p -addr :5640 -backend cli
# Run with debug logging
ANTHROPIC_API_KEY=sk-... ./llm9p -addr :5640 -debug
Testing
# Run all tests
go test ./...
# Run with coverage
go test -cover ./...
# Test specific package
go test ./internal/protocol/...
go test ./internal/llmfs/...
Development Workflow
# Install dependencies
go mod tidy
# Format code
go fmt ./...
# Vet code
go vet ./...
# Build
go build -o llm9p ./cmd/llm9p
Architecture Overview
Project Structure
llm9p/
├── cmd/
│ └── llm9p/
│ └── main.go # Entry point, CLI flags, server setup
├── internal/
│ ├── protocol/ # 9P2000 protocol implementation
│ │ ├── protocol.go # Message types, constants, encoding
│ │ ├── message.go # Individual message types
│ │ ├── server.go # Connection handling
│ │ └── fs.go # File/Dir interfaces, base implementations
│ ├── llm/ # LLM client wrapper
│ │ └── client.go # Anthropic API integration
│ └── llmfs/ # LLM filesystem implementation
│ ├── root.go # Root directory construction
│ ├── ask.go # Ask file (shim pattern)
│ ├── state.go # Model, temperature files
│ ├── system.go # System prompt file
│ ├── tokens.go # Read-only token counter
│ ├── new.go # Conversation reset trigger
│ ├── context.go # Conversation history
│ ├── example.go # Usage examples
│ └── stream.go # Streaming interface
├── go.mod
├── go.sum
├── README.md
└── CLAUDE.md
Key Components
- Protocol Layer (
internal/protocol/)- Implements 9P2000 protocol
- No external dependencies (stdlib only)
FileandDirinterfaces define the filesystem abstraction
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.
- 5d ago First seen · 361 lines · 2,810 tokens per session scan A 342db5426836
llm9p CLAUDE.md is an instructions file published in the GitHub repository NERVsystems/llm9p (46 stars, last pushed 3d ago), licensed MIT. It adds 2,810 tokens to every session, about $0.0140 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
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
GhidrAssistMCP CLAUDE.md
Claude Code instructions for symgraph/GhidrAssistMCP, covering claude.md, build and development commands, building the extension, set ghidrainstalldir environment variable first and build the extension.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
intervals-icu-mcp CLAUDE.md
Claude Code instructions for hhopke/intervals-icu-mcp, covering claude.md, project overview, development commands, architecture (quick reference) and tool categories.
pfsense-mcp-server AGENTS.md
AGENTS.md instructions for night4me/pfsense-mcp-server, covering pfsense mcp server, architecture and security, development workflow, long-running validation and test parallelism.
pbi-context CLAUDE.md
Instructions for Osc2405/pbi-context, covering estado actual (actualizado 2026-07-15), actualización 2026-08-03 — rename pbi-docs → pbi-context, 0. contexto del proyecto (no re-investigar, ya validado), 1. feature obligatoria: soporte .pbip / tmdl and por qué es obligatoria (contexto de mercado, no opinable).