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/incidentfox/box/claude-mdgit clone --depth 1 https://github.com/incidentfox/boxWhat 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 | $0.01268 | $0.01268 |
| Opus 5 | $0.00634 | $0.00634 |
| Sonnet 5 | $0.00254 | $0.00254 |
| Haiku 4.5 | $0.00127 | $0.00127 |
Grade A, and why
box 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.
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.
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 · 77 lines · 1,268 tokens per session scan A 57665e4ea19c
box CLAUDE.md is an instructions file published in the GitHub repository incidentfox/box (5 stars, last pushed 4d ago), licensed GPL-3.0. It adds 1,268 tokens to every session, about $0.0063 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
nanobot AGENTS.md
AGENTS.md instructions for HKUDS/nanobot, covering project overview, development commands, python: run single test / lint, strict type checking (matches ci) and gateway.
happy AGENTS.md
Instructions for slopus/happy, covering agent workflow and sync to main.
avibe AGENTS.md
Instructions for avibe-bot/avibe, covering agent guidelines for avibe, 1. project overview, 2. design philosophy and architecture, core rule: fix at the highest appropriate layer and codebase map.
claude-code-slack-channel AGENTS.md
Instructions for jeremylongshore/claude-code-slack-channel, covering agents.md — ccsc (claude-code-slack-channel), what this repo is, if you're helping a new user install this, critical setup gotchas (the silent killers) and build / test / dev commands.
kiro-discord-bot AGENTS.md
Instructions for nczz/kiro-discord-bot, covering agents.md — kiro-discord-bot agent contract, source-of-truth map, non-negotiable principles, architecture boundaries and discord output and i18n.
claude-threads CLAUDE.md
Instructions for anneschuth/claude-threads, covering claude code instructions for claude-threads, what this project does, contribution conventions, architecture overview and multi-platform support.