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/thurbeen/thurbox/claude-mdgit clone --depth 1 https://github.com/Thurbeen/thurboxWhat 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 | $0.03517 | $0.03517 |
| Opus 5 | $0.01758 | $0.01758 |
| Sonnet 5 | $0.00703 | $0.00703 |
| Haiku 4.5 | $0.00352 | $0.00352 |
Grade A, and why
thurbox 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 3d 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 — 277 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
Thurbox is a multi-session coding-agent TUI orchestrator built with Rust. It runs multiple coding-agent CLI instances (Claude Code, Codex, Antigravity, opencode, aider, … — any CLI you define) inside persistent tmux sessions, rendered as terminal panels via ratatui + tui-term. Sessions survive crashes/restarts because tmux keeps the processes alive.
Each session picks which agent to run from a declarative
registry (~/.config/thurbox/agents.toml). Thurbox is
agent-neutral: it knows nothing about any agent's model,
permissions, prompts, or tools — only how to launch the CLI with
the right command + args. Each agent uses its own default
config (bake a model or other flags into the agent's args if
you want them).
Build & Development Commands
The reproducible dev environment is a Nix flake (flake.nix, pins the Rust
toolchain + tmux/shellcheck/node/cargo-tools/just/demo stack) — enter it with
nix develop (or direnv allow once; see .envrc). Non-Nix fallback:
scripts/install-dev-tools.sh. Task entrypoint is just (justfile); full
guide in docs/DEVELOPMENT.md.
just build # cargo build --bin thurbox --bin thurbox-cli
just test # cargo nextest run --all
just lint # fmt-check + clippy + deny + rumdl + shellcheck + the 3 Lua gates
cargo check --all # Type check (bare cargo still works)
cargo build --release # Release build (LTO, stripped)
To run thurbox in an isolated sandbox use scripts/dev/sandbox.sh (a.k.a.
just sandbox*). By default it does thurbox-only isolation: redirects only
thurbox's config/data into the sandbox (via the THURBOX_CONFIG_DIR/
THURBOX_DATA_DIR overrides paths.rs honors) while keeping your real HOME —
so your authenticated agent CLIs (claude/codex/…) work — and puts dev
target/debug first on PATH so an agent hook's thurbox-cli hits the sandbox DB.
It also names the sandbox's tmux socket outright (THURBOX_SOCKET, = $TBX_DEV_SOCKET): a relocated THURBOX_DATA_DIR otherwise derives one of its
own, and teardown kills the socket by name.
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.
- 3d ago First seen · 277 lines · 3,517 tokens per session scan A 356bcb3dc3e2
thurbox CLAUDE.md is an instructions file published in the GitHub repository Thurbeen/thurbox (57 stars, last pushed 3d ago), licensed MIT. It adds 3,517 tokens to every session, about $0.0176 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.