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/agents-mdgit clone --depth 1 https://github.com/8b-is/smart-treeWhat 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 | $0.00783 | $0.00783 |
| Opus 5 | $0.00392 | $0.00392 |
| Sonnet 5 | $0.00157 | $0.00157 |
| Haiku 4.5 | $0.00078 | $0.00078 |
Grade A, and why
smart-tree AGENTS.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 2d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
This guide gives contributors the essentials for working on Smart Tree in this repository. Keep updates concise and run the pre-commit checks before opening a PR.
Project Structure & Module Organization
src/: Main Rust crate. Key areas:main.rs/cli.rs(entry & clap args),scanner.rs(walks the filesystem),formatters/(output formats),mcp/(JSON-RPC tools),mem8/(persistence),web_dashboard/(web UI backend), andbin/targets forst,mq,m8,n8x.scripts/: Automation (manage.sh,build-and-install.sh) plus helper shell functions.tests/: Rust integration tests; fixtures live alongside intest,test_files, andtest-dirs.docs/andexamples/: User-facing guides and sample outputs.marqant/: Compression submodule;expert_prompt_engineer/: secondary workspace crate.
Build, Test, and Development Commands
./scripts/manage.sh test— pre-commit bundle:cargo test+cargo clippy -D warnings+cargo fmt --check.cargo build --release— optimized binaries with TUI built-in; use--features fullfor local LLM (candle).cargo run --bin st -- --help— smoke-test the CLI; add flags like--mode ai --compressas needed.cargo testorcargo test name -- --exact --nocapture— run all or targeted tests with output.cargo fmt --all -- --checkandcargo clippy -- -D warnings— enforce style/lints when iterating../scripts/build-and-install.sh— rebuild and install locally, clearing shell command cache.
Coding Style & Naming Conventions
- Rust 2021, 4-space indent. Keep functions small; prefer composition over long match blocks.
- Use
anyhow::Resultwith.context(...); avoid panics in library code. - File/module names snake_case; types/enums struct PascalCase; CLI flags stay kebab-case to match
cli.rs. - Logging via
tracingmacros; keep comments brief and in the existing light, direct tone.
Testing Guidelines
- Primary suite:
cargo test; async tests use#[tokio::test]. - Integration coverage in
tests/; data fixtures undertest/test_files/test-dirs. - CLI/regression scripts (
test_spicy.sh,test_feature_flags.sh, etc.) can be run directly withbash. - For verbose diagnostics:
RUST_LOG=debug cargo test -- --nocapture. - Aim for zero clippy warnings and add tests for new branches or error paths.
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.
- 2d ago First seen · 42 lines · 783 tokens per session scan A 26127111f3b8
smart-tree AGENTS.md is an instructions file published in the GitHub repository 8b-is/smart-tree (265 stars, last pushed 1mo ago), licensed MIT. It adds 783 tokens to every session, about $0.0039 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
cli AGENTS.md
Instructions for googleworkspace/cli, covering agents.md, project overview, build & test, changesets and architecture.
turso AGENTS.md
Instructions for tursodatabase/turso, covering turso agent guidelines, quick reference, testing, running tests and test organization.
memvid CLAUDE.md
Claude Code instructions for memvid/memvid, covering claude.md, project overview, architecture, core components and file format (.mv2).
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
codemap CLAUDE.md
Instructions for JordanCoin/codemap, covering 🛑 stop — run codemap before any task, repo root requirement (critical) and required usage.
ton-rs AGENTS.md
Instructions for ston-fi/ton-rs, covering ton-rs agent guide, repository, boundaries, public api and ton invariants.