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/0xferrous/agent-box/agents-mdgit clone --depth 1 https://github.com/0xferrous/agent-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 | $0.00373 | $0.00373 |
| Opus 5 | $0.00187 | $0.00187 |
| Sonnet 5 | $0.00075 | $0.00075 |
| Haiku 4.5 | $0.00037 | $0.00037 |
Grade A, and why
agent-box 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 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.
What it actually says
- use
nix develop --commandto run the commands in the flake's devshell - use conventionalcommits.org pattern when writing commit messages
pre commit
- format code with
cargo fmt - check code with
cargo check - check clippy with
cargo clippy - always keep the docs and README files in sync with the code changes (root and crate-level READMEs)
- keep the table of contents in the root
README.mdup to date whenever a change is made
image
The image flake uses a custom docker.nix from the nix input (github:0xferrous/nix/extra-args).
To get the nix store path of the nix flake input:
nix eval --raw --impure --expr '(builtins.getFlake (toString ./image)).inputs.nix'
# Returns: /nix/store/<hash>-source
To read the docker.nix file from that input:
cat $(nix eval --raw --impure --expr '(builtins.getFlake (toString ./image)).inputs.nix')/docker.nix
This is referenced in image/flake.nix as:
pkgs.callPackage "${nix}/docker.nix" { ... }
wrappers
- implement wrapper binaries in Rust (keep wrapper runtime language consistent across
wrappers/)
portal ADR
- Portal architecture decisions are tracked in
adr/. - Current accepted ADRs:
adr/0001-agent-portal.mdadr/0002-transparent-portal-wrappers.md
- For portal work, keep implementation and configuration aligned with these ADRs.
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 · 45 lines · 373 tokens per session scan A d65f282c3c18
agent-box AGENTS.md is an instructions file published in the GitHub repository 0xferrous/agent-box (35 stars, last pushed 3mo ago), licensed MIT. It adds 373 tokens to every session, about $0.0019 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
docker-nixuser AGENTS.md
Instructions for grigio/docker-nixuser, covering development guide, ci publishing (critical), multi-platform ci builds, flake auto-update and docker image.
microsandbox AGENTS.md
AGENTS.md instructions for superradcompany/microsandbox, covering agents.md, scope, project map, design principles and backward compatibility review.
sandboxd AGENTS.md
Instructions for tastyeffectco/sandboxd, covering agents.md — operating sandboxd, what this is, prerequisites, install and core api.
MultiGen CLAUDE.md
Instructions for lingyuanli/MultiGen, covering claude.md, architecture, development commands, full stack (docker) and api (local).
agentbox CLAUDE.md
Instructions for madarco/agentbox, covering agentbox — context for claude code, architecture overview, important notes, testing / verifying and conventions.
ephemeral-sandbox CLAUDE.md
Instructions for Ephemeral-AI-Lab/ephemeral-sandbox, covering claude.md, project, engineering practice (required), build & test and sandbox tools.