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/papercomputeco/stereos/agents-mdgit clone --depth 1 https://github.com/papercomputeco/stereOSWrote 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/papercomputeco/stereos/agents-md)<a href="https://agentmods.dev/instructions/papercomputeco/stereos/agents-md"><img src="https://agentmods.dev/badge/instructions/papercomputeco/stereos/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 | $0.00884 | $0.00884 |
| Opus 5 | $0.00442 | $0.00442 |
| Sonnet 5 | $0.00177 | $0.00177 |
| Haiku 4.5 | $0.00088 | $0.00088 |
Grade B, and why
stereOS 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 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
│ ├── agent.nix # Agent user: restricted shell, ~/workspace, sudo denial, options The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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 · 78 lines · 884 tokens per session scan B e55b4fdb41ab
stereOS AGENTS.md is an instructions file published in the GitHub repository papercomputeco/stereOS (493 stars, last pushed yesterday), with no licence file. It adds 884 tokens to every session, about $0.0044 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.
Other instructions, from other repositories
nxv AGENTS.md
Instructions for utensils/nxv, covering agents.md, project overview, development environment, build commands and nix flake outputs.
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.
hoenn AGENTS.md
AGENTS.md instructions for alyraffauf/hoenn, covering work in hoenn, check a change, deploy deliberately and keep secrets out of git.
nix-config AGENTS.md
Instructions for dliberalesso/nix-config, covering agent instructions for nix-config, build/lint/test commands, architecture guidance, architecture and common patterns.
nix-config CLAUDE.md
Instructions for softinio/nix-config, covering claude.md, architecture, flake structure, user profiles and machine configuration.
tuinix CLAUDE.md
Instructions for timlinux/tuinix, a project described as: A pure terminal-based Linux experience built on NixOS with ZFS encryption.