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/gradion-ai/ipybox/agents-mdgit clone --depth 1 https://github.com/gradion-ai/ipyboxWrote 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/gradion-ai/ipybox/agents-md)<a href="https://agentmods.dev/instructions/gradion-ai/ipybox/agents-md"><img src="https://agentmods.dev/badge/instructions/gradion-ai/ipybox/agents-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 | $0.00515 | $0.00515 |
| Opus 5 | $0.00258 | $0.00258 |
| Sonnet 5 | $0.00103 | $0.00103 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
ipybox 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 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
- Documentation:
docs/ - Project description:
docs/index.md - Internal documentation:
- Architecture:
docs/internal/architecture.md - Testing:
docs/internal/testing.md
- Architecture:
- Source modules:
ipybox/code_exec.py: CodeExecutor, main APIipybox/kernel_mgr/: KernelGateway and KernelClientipybox/mcp_server.py: MCPServeripybox/utils.py: shared utilities
- Tests:
tests/unit/: unit teststests/integration/: integration tests
Directory-specific Guidelines
docs/AGENTS.md: documentation authoringtests/AGENTS.md: testing conventions and utilities
Development Commands
uv sync # Install/sync dependencies
uv add [--dev] [-U] <dep> # Add a dependency (--dev for dev-only, -U to upgrade)
uv run <command> # Run <command> in project's venv
uv run invoke cc # Run code checks (auto-fixes formatting, mypy errors need manual fix)
uv run invoke test # Run all tests
uv run invoke ut # Run unit tests only
uv run invoke it # Run integration tests only
uv run invoke test --cov # Run tests with coverage
uv run invoke build-docs # Build docs
uv run invoke serve-docs # Serve docs at localhost:8000
uv run pytest -xsv tests/integration/test_[name].py # Single test file
uv run pytest -xsv tests/integration/test_[name].py::test_name # Single test
invoke cconly checks files under version control. Rungit addon new files first.
Docstring Guidelines
- Use mkdocs-formatter and mkdocs-docstrings skills for docstrings
- Use Markdown formatting, not reST
- Do not add module-level docstrings
Coding Guidelines
- All function parameters and return types must have type hints
- Modern union syntax:
str | Noneinstead ofOptional[str] - Prefer
match/caseoverisinstance()for type dispatch - Package
__init__.pyfiles are re-exports only; do not define functions or classes in them
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 · 54 lines · 515 tokens per session scan A 167e4c6849a3
ipybox AGENTS.md is an instructions file published in the GitHub repository gradion-ai/ipybox (73 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 515 tokens to every session, about $0.0026 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
tensorlake AGENTS.md
Instructions for tensorlakeai/tensorlake, a project described as: Tensorlake is a serverless runtime for sandboxes and deploying background agentic applications.
tensorlake CLAUDE.md
Instructions for tensorlakeai/tensorlake, covering claude.md, project overview, common commands, install dependencies and build and format code (black + isort).
nono AGENTS.md
AGENTS.md instructions for nolabs-ai/nono, covering nono - development guide, project overview, library vs cli boundary, build & test and build everything.
infra CLAUDE.md
Instructions for e2b-dev/infra, covering claude.md, project overview, common development commands, setup & environment and switch between environments (prod, staging, dev).
mcpc CLAUDE.md
Claude Code instructions for apify/mcpc, covering claude.md, project overview, build and development commands, install dependencies and build the project.
llm-sandbox CLAUDE.md
Instructions for vndee/llm-sandbox, covering llm sandbox - ai assistant guide, project overview, core architecture, key components and project structure.