void-box AGENTS.md

Project instructions for VoidBox, a lightweight micro-virtual-machine runtime that runs agents in isolated environments. They describe its architecture, design proposal process, code navigation, testing, commits, pull requests, and documentation style.

In plain words
What is it for?
Use them when working on VoidBox code, especially for navigating code with language-server tools, preparing design proposals, writing commits or pull requests, and documenting changes.
Why use it?
They give coding agents project-specific rules for making changes consistently and safely. They also explain when a larger change needs an RFC (a written proposal) and an ADR (a recorded architecture decision).

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/the-void-ia/void-box/agents-md
Clone the repo
git clone --depth 1 https://github.com/the-void-ia/void-box

Made for: Codex, OpenCode.

Per session 18,103 This file is loaded in full into every session.
When invoked 18,103 The same file — it is already loaded in full.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.18103 $0.18103
Opus 5 $0.09052 $0.09052
Sonnet 5 $0.03621 $0.03621
Haiku 4.5 $0.01810 $0.01810

Measured 2d ago against content hash 26b029507c13, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

void-box AGENTS.md scanned grade B with 1 finding 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

# sudo dnf install -y gcc-aarch64-linux-gnu sysroot-aarch64-fc43-glibc
AGENTS.md · 1,422 lines

How it starts

The opening of the file, as written. The whole thing — 1,422 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — VoidBox

VoidBox is a lightweight micro-VM runtime for sandboxed execution. It boots a guest agent from initramfs, optionally performs an OCI root switch, and exposes a host↔guest API over vsock. This file covers architecture, testing, validation, and debugging guidance for agents working on the project.

Design proposals: RFC + ADR process

Changes that are large, complex, cross-cutting, or that need peer review before commitment go through an RFC (proposal + discussion) in docs/rfc/; the resulting load-bearing decisions are recorded as ADRs (atomic, immutable, superseded-not-edited) in docs/adr/. Small, local, obvious changes skip the RFC and go straight to a PR. The full process — when to write an RFC, numbering, statuses, and templates — is documented once in docs/rfc/README.md.

Code intelligence

Always prefer LSP operations (goToDefinition, findReferences, hover, documentSymbol, workspaceSymbol, etc.) over Grep/Glob for code navigation. LSP provides compiler-aware results that understand types, scopes, and cross-file relationships. Fall back to Grep/Glob only for pattern-based searches LSP doesn't cover (comments, config files, non-Rust files).

Commit and PR messages

Write commit message bodies and pull-request descriptions as Markdown, with each paragraph on a single line — do not hard-wrap prose to a fixed column. The renderer (GitHub, git log viewers) wraps it for display; manual line breaks mid-paragraph render as ragged text and produce noisy diffs on edits. Keep the commit subject line short (~72 chars), and use blank lines to separate paragraphs and normal Markdown for lists. Reserve hard line breaks for content that is genuinely line-oriented (lists, tables, code blocks).

Do not add AI-agent attribution anywhere — no "Generated by"/"Co-Authored-By" tool credits, no session links, no "written with " notes — in commit messages, PR titles or descriptions, code, comments, or docs. The work stands on its own; tooling used to produce it is not part of the record.

Read the full file on GitHub · 1,422 lines

Changes

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.

  1. 2d ago First seen · 1,422 lines · 18,103 tokens per session scan B 26b029507c13

Subscribe to this mod's changes

void-box AGENTS.md is an instructions file published in the GitHub repository the-void-ia/void-box (88 stars, last pushed 5d ago), licensed Apache-2.0. It adds 18,103 tokens to every session, about $0.0905 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.