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/lukastk/boxyard/agents-mdgit clone --depth 1 https://github.com/lukastk/boxyardWhat 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 | $0.01791 | $0.01791 |
| Opus 5 | $0.00896 | $0.00896 |
| Sonnet 5 | $0.00358 | $0.00358 |
| Haiku 4.5 | $0.00179 | $0.00179 |
Grade A, and why
boxyard 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 yesterday.
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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Overview
Boxyard is a Python CLI tool for managing and syncing folders ("boxes") across local and remote storage using rclone. It tracks box metadata, supports group management, and provides bidirectional sync with conflict detection.
Development Commands
# Setup
uv sync # Install dependencies to .venv
direnv allow # Auto-load environment
nbl install-hooks # Git hooks for notebook validation
# Development (after editing .pct.py files)
nbl export # Export pts → src/boxyard/ (regenerates the package)
nbl clean # Clean notebook outputs
# Testing
pytest src/tests/ # Run all tests
pytest src/tests/unit/config/test_config_loading.py -v # Run specific test file
nbl test # Test notebooks execute without errors
# Building
uv build # Create distribution in dist/
# Publishing
uv build # Create distribution in dist/
uv publish # Upload to PyPI
Architecture
Notebook-First Development (nblite)
Critical rule: Never edit files in src/boxyard/ directly — they are autogenerated from pts/ and will be overwritten.
The nbs/ (Jupyter notebook) layer was removed (commit 3147b8a) because it caused git friction; nbs/ is now gitignored and absent. pts/ (percent-format Python) is the source of truth. After editing a .pct.py, run nbl export to regenerate the package — there is no .ipynb round-trip to sync back to anymore.
The export pipeline (defined in nblite.toml):
pts/mod/*.pct.py → src/boxyard/*.py
pts/tests/*.pct.py → src/tests/*.py
pts/- Percent-format Python files (source of truth, edit these)src/boxyard/- Generated Python package (DO NOT EDIT)src/tests/- Generated test files
Note: nblite.toml still declares vestigial nbs -> pts pipeline legs even though nbs/ no longer exists — harmless, but the forward pts -> lib (src) leg is the one that matters.
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.
- yesterday First seen · 154 lines · 1,791 tokens per session scan A 92b34a464f13
boxyard AGENTS.md is an instructions file published in the GitHub repository lukastk/boxyard (0 stars, last pushed 2d ago), licensed MIT. It adds 1,791 tokens to every session, about $0.0090 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
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.
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).
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.