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/8b-is/smart-tree/claude-mdgit clone --depth 1 https://github.com/8b-is/smart-treeWrote 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/8b-is/smart-tree/claude-md)<a href="https://agentmods.dev/instructions/8b-is/smart-tree/claude-md"><img src="https://agentmods.dev/badge/instructions/8b-is/smart-tree/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 | $0.01650 | $0.01650 |
| Opus 5 | $0.00825 | $0.00825 |
| Sonnet 5 | $0.00330 | $0.00330 |
| Haiku 4.5 | $0.00165 | $0.00165 |
Grade A, and why
smart-tree 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 — 120 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
Smart Tree (st) is a fast, AI-friendly directory visualization tool written in Rust. It provides 30+ MCP tools for AI assistants and is 10-24x faster than traditional tree.
Build & Development Commands
cargo build # Debug build
cargo build --release # Release build (LTO enabled, stripped)
cargo test # Run all tests
cargo test --release # Run performance tests
cargo test <test_name> # Run a single test
cargo run --bin st -- --help # Run locally without installing
cargo fmt # Format code
cargo clippy -- -D warnings # Lint (zero-warning policy)
./scripts/manage.sh test # Pre-commit bundle: test + clippy + fmt --check
./scripts/build-and-install.sh # Build and install locally (clears shell cache)
Run ./scripts/manage.sh test before opening a PR — it is the canonical pre-commit gate. Async tests use #[tokio::test]; for verbose diagnostics use RUST_LOG=debug cargo test -- --nocapture.
After rebuilding, if st --version hangs, run hash -r to clear your shell's binary cache.
Architecture
Thin-client + daemon model: The st CLI binary is a thin client that spawns an async daemon (std) for heavy lifting and persistent state. The daemon exposes an HTTP API on port 28428 (default).
CLI → Daemon Flow
Most st commands follow this path:
main.rsparses CLI args, initializes logging- Exclusive modes run locally and exit:
--mcp,--version,--completions,--man,--security-scan,--terminal,--dashboard,--http-daemon,--guardian-daemon, daemon control flags - Everything else (the common case): auto-starts daemon if needed, builds a
CliScanRequest(defined indaemon_cli.rs), sends HTTP POST to/cli/scan, prints response
Daemon Communication
- CLI ↔ Daemon: HTTP/JSON on port 28428, authenticated via Bearer token stored at
~/.st/daemon.token - Daemon ↔ Daemon:
st-protocolbinary wire protocol (6502-inspired opcodes) over Unix sockets — this is NOT used for CLI-daemon communication - Auto-spawn:
DaemonClient::ensure_running()spawns daemon in background withsetsid(Unix) orDETACHED_PROCESS(Windows), retries with exponential backoff (5 attempts, 100ms→1600ms)
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 · 120 lines · 1,650 tokens per session scan A 897b6caef93b
smart-tree CLAUDE.md is an instructions file published in the GitHub repository 8b-is/smart-tree (266 stars, last pushed 1mo ago), licensed MIT. It adds 1,650 tokens to every session, about $0.0083 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
paths-le AGENTS.md
AGENTS.md instructions for nolindnaidoo/paths-le, covering agents.md — paths-le, what this is, architecture, code style and control flow.
paths-le CLAUDE.md
Claude Code instructions for nolindnaidoo/paths-le, covering claude.md, where to look, gates and things that will bite you.
paths-le copilot-instructions.md
Copilot instructions for nolindnaidoo/paths-le, covering contributor and agent instructions, non-negotiables and before you commit.
paths-le GEMINI.md
Gemini CLI instructions for nolindnaidoo/paths-le, covering contributor and agent instructions, non-negotiables and before you commit.
turso AGENTS.md
Instructions for tursodatabase/turso, covering turso agent guidelines, quick reference, testing, running tests and test organization.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.