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/meoyawn/vps-agent/agents-mdgit clone --depth 1 https://github.com/meoyawn/vps-agentWrote 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/meoyawn/vps-agent/agents-md)<a href="https://agentmods.dev/instructions/meoyawn/vps-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/meoyawn/vps-agent/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 | $0.00244 | $0.00244 |
| Opus 5 | $0.00122 | $0.00122 |
| Sonnet 5 | $0.00049 | $0.00049 |
| Haiku 4.5 | $0.00024 | $0.00024 |
Grade A, and why
vps-agent 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 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.
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
AGENTS.md
Project vocab/refs
- vps: remote VPS
- Taskfile
- README
Rules
- T3 Code runs on Node.js. Use
nubx -y t3@latest ...for its package runner; never usenpx, Bun, or a global T3 package. nub/nubxare already provisioned by Ansible. Do not replace them withnpx,bunx, or another package runner.- Keep existing Bun-backed repository tooling unchanged; do not use Bun for Node/T3 workflows.
- never write yaml extension as
.yml, do.yaml - never skip running
task verifyafteransible/**/*change - never run
task verifywhen working withgit - never use
pip, useuv - never use
bashin Markdown code blocks, useshinstead - never leak IPs or secrets in git history, this repo is open source
- never change task names in Taskfile without syncing those task names in README
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 · 21 lines · 244 tokens per session scan A de72fe7e5ad5
vps-agent AGENTS.md is an instructions file published in the GitHub repository meoyawn/vps-agent (1 stars, last pushed 3d ago), licensed Unlicense. It adds 244 tokens to every session, about $0.0012 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
libtmux-mcp AGENTS.md
AGENTS.md instructions for tmux-python/libtmux-mcp, covering agents.md, what is here, which policy applies, change discipline and references.
agentcrew-dev-skills AGENTS.md
AGENTS.md instructions for okqixiaobao727-design/agentcrew-dev-skills, covering agents.md and validating your work.
j3w1zsh AGENTS.md
AGENTS.md instructions for j3w1/j3w1zsh, covering j3w1zsh agent instructions, purpose and authority, start every run, security and privacy and platform and installer contract.
review-switch AGENTS.md
AGENTS.md instructions for okqixiaobao727-design/review-switch, covering review-switch, agent skills, issue tracker, triage labels and domain docs.
remocli AGENTS.md
Instructions for whulxc/remocli, covering remocli maintenance guide, what matters first, primary entrypoints, default troubleshooting flow and 1. identify the active mode.
libtmux-mcp CLAUDE.md
Claude Code instructions for tmux-python/libtmux-mcp, a project described as: MCP for tmux, powered by libtmux.