box AGENTS.md

Project instructions for coding agents working in the incidentfox/box codebase. They explain the agent’s role, safety rules, contribution process, and protected main branch.

In plain words
What is it for?
Following repository rules, checking what an agent is allowed to do, contributing changes, and exploring the code safely.
Why use it?
They prevent agents from making unsafe changes or working in the wrong way. They also clarify when changes must be submitted as a pull request.

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/incidentfox/box/agents-md
Clone the repo
git clone --depth 1 https://github.com/incidentfox/box

Made for: Codex, OpenCode.

Per session 970 This file is loaded in full into every session.
When invoked 970 The same file — it is already loaded in full.
Security scan B 2 findings. Scan, not verified.
Origin unknown 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 $0.00970 $0.00970
Opus 5 $0.00485 $0.00485
Sonnet 5 $0.00194 $0.00194
Haiku 4.5 $0.00097 $0.00097

Measured 2d ago against content hash 08077fc06cb1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

box AGENTS.md scanned grade B with 2 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

mention this to the user — they can dial it back in `~/.claude/settings.json`.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

4. **Verify, then report:** `curl -s -H "Authorization: Bearer $TOKEN" localhost:$PORT/api/config`
AGENTS.md · 58 lines

The source is not reproduced here

Licensed GPL-3.0

The repository is licensed GPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

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 · 58 lines · 970 tokens per session scan B 08077fc06cb1

Subscribe to this mod's changes

box AGENTS.md is an instructions file published in the GitHub repository incidentfox/box (5 stars, last pushed 3d ago), licensed GPL-3.0. It adds 970 tokens to every session, about $0.0049 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.