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/samoradc/tetrad/claude-mdgit clone --depth 1 https://github.com/SamoraDC/TetradWrote 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/samoradc/tetrad/claude-md)<a href="https://agentmods.dev/instructions/samoradc/tetrad/claude-md"><img src="https://agentmods.dev/badge/instructions/samoradc/tetrad/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 | $0.02316 | $0.02316 |
| Opus 5 | $0.01158 | $0.01158 |
| Sonnet 5 | $0.00463 | $0.00463 |
| Haiku 4.5 | $0.00232 | $0.00232 |
Grade A, and why
Tetrad 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 — 268 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
Tetrad is a high-performance MCP (Model Context Protocol) server written in Rust that orchestrates three CLI code evaluation tools (Codex, Gemini CLI, Qwen) to validate code produced by Claude Code. It implements a quadruple consensus protocol where no code is accepted without unanimous approval from four intelligences: the three external evaluators + Claude Code itself.
Current Status: Phases 1-5 complete. The project has a functional MCP server, consensus engine, ReasoningBank with SQLite, LRU cache, and hook system. Phase 6 (Release) is in progress - published to crates.io and npm.
Build and Development Commands
# Build
cargo build
cargo build --release
# Run
cargo run -- <command>
# Test
cargo test # All tests
cargo test --lib # Unit tests only
cargo test --test <test_name> # Single integration test
# Lint and format
cargo clippy
cargo fmt
cargo fmt --check
# Check without building
cargo check
# Documentation
cargo doc --open
# Install locally for testing
cargo install --path .
CLI Commands
tetrad init # Initialize config in current directory
tetrad serve # Start MCP server (used by Claude Code)
tetrad status # Show CLI status (codex, gemini, qwen)
tetrad config # Interactive configuration (dialoguer)
tetrad doctor # Diagnose configuration issues
tetrad version # Show version
tetrad evaluate -c CODE # Manual code evaluation (without MCP)
tetrad history # Show evaluation history from ReasoningBank
tetrad export -o FILE # Export ReasoningBank patterns
tetrad import FILE # Import patterns into ReasoningBank
Architecture
Claude Code → MCP Protocol (stdio) → Tetrad Server (Rust)
│
┌─────────────────────┼─────────────────────┐
▼ ▼ ▼
Codex CLI Gemini CLI Qwen CLI
(syntax) (architecture) (logic)
│ │ │
└─────────────────────┼─────────────────────┘
▼
Consensus Engine
│
┌─────────────┴─────────────┐
▼ ▼
Cache LRU ReasoningBank
(results) (SQLite)
RETRIEVE→JUDGE→DISTILL→CONSOLIDATE
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 · 268 lines · 2,316 tokens per session scan A 7299d8bc2d86
Tetrad CLAUDE.md is an instructions file published in the GitHub repository SamoraDC/Tetrad (1 stars, last pushed 7mo ago), licensed MIT. It adds 2,316 tokens to every session, about $0.0116 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
agent-exporter AGENTS.md
Instructions for ihatenodejs/agent-exporter, covering development commands, example: bun run dev sync --provider opencode, creates compiled binary at dist/agent-exporter, then use: agent-exporter and architecture.
nvim-gemini-companion GEMINI.md
Gemini CLI instructions for gutsavgupta/nvim-gemini-companion, covering nvim-gemini-companion, directory structure, coding guidelines, commit messages and format.
agent-exporter CLAUDE.md
Instructions for ihatenodejs/agent-exporter, a project described as: Export usage statistics from various harnesses.
spec-kitty AGENTS.md
AGENTS.md instructions for Priivacy-ai/spec-kitty, covering spec kitty development guidelines, ⚠️ critical: load the project charter first, ⚠️ critical: template source location, ⚠️ critical: use canonical sources, never improvise and ⚠️ critical: git workflow — no direct pushes to origin/main.
coral CLAUDE.md
Instructions for cdknorow/coral, covering claude.md - coral go, mission, testing, go unit tests and legacy parity tools (historical reference).
sessionview AGENTS.md
AGENTS.md instructions for tyql688/sessionview, covering sessionview, commands, app / frontend, gates must pass under both feature sets: default (gui) and and --no-default-features --features headless.