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/cyyprezz/codex-serverops-mcp/agents-mdgit clone --depth 1 https://github.com/cyyprezz/codex-serverops-mcpWrote 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/cyyprezz/codex-serverops-mcp/agents-md)<a href="https://agentmods.dev/instructions/cyyprezz/codex-serverops-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/cyyprezz/codex-serverops-mcp/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 | $0.00439 | $0.00439 |
| Opus 5 | $0.00219 | $0.00219 |
| Sonnet 5 | $0.00088 | $0.00088 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
codex-serverops-mcp 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.
How it starts
The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ServerOps project contract
ServerOps is a client-neutral operations product for people who need to operate explicitly configured Linux servers from ordinary AI applications. First-class clients are Codex/ChatGPT and Claude Code. IDE-specific integrations are thin compatibility wrappers, not a product direction.
Primary users include freelancers and agencies with customer servers, small and medium Linux operators, support and project owners, and technically interested users without a daily SSH workflow. ServerOps must be easier to start than a traditional SSH workflow, retain useful state outside disposable AI clients, return understandable evidence instead of raw-output floods, and require no ServerOps software on the Linux host.
Architecture boundaries
- Keep one MCP core and thin client distributions.
- Preserve package names, entry points, configuration paths, protocol versions, credentials, audit, sessions, structured files, and all unknown-outcome contracts unless a versioned migration explicitly changes them.
- Credentials and host-key decisions stay in visible local windows and never enter MCP arguments, logs, manifests, or prompts.
- Never automatically retry a mutation after
outcome_unknown,file_outcome_unknown,elevation_outcome_unknown, a lost connection, or an effectful timeout. - Add a core function only when durable state, large or binary data, resume, atomicity, idempotency, event delivery, verification, or multi-client coordination justifies it.
- Do not add promptable pseudo-tools for ordinary
df,free,ps,top,systemctl, Docker, journal, process-kill, generic database, dump, or cron commands. - Do not claim exactly-once effects. Use receipts, idempotency, verification, and explicit unknown outcomes where later phases introduce durable operations.
- Bootstrap may prepare only ServerOps-owned local state. Client configuration, Scheduled Tasks, SSH files, profiles, server contact, administrator rights, and unmanaged files require separate explicit authority.
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 · 36 lines · 439 tokens per session scan A 4b9a35ed7b62
codex-serverops-mcp AGENTS.md is an instructions file published in the GitHub repository cyyprezz/codex-serverops-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 439 tokens to every session, about $0.0022 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
Pake copilot-instructions.md
Copilot instructions for tw93/Pake, a project described as: 🤱🏻 Turn any webpage into a desktop app with one command.
nuclear AGENTS.md
AGENTS.md instructions for nukeop/nuclear, covering agents.md, project overview, packages, commands and development.
agent-zero AGENTS.md
AGENTS.md instructions for agent0ai/agent-zero, covering agent zero dox, purpose, project, root ownership and project-wide contracts.
swift-tui AGENTS.md
Instructions for SwiftTUI/swift-tui, covering agents.md, build & test commands, architecture (one-page summary), development guidelines and code style.
best-claude-hud AGENTS.md
Instructions for GaoSSR/best-claude-hud, covering project agent instructions and release work.
AutoControlGUI CLAUDE.md
Instructions for Integration-Automation/AutoControlGUI, covering claude.md — autocontrol, project overview, architecture, development commands and feature delivery rules.