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/internetworklab/cloudping/agents-mdgit clone --depth 1 https://github.com/internetworklab/cloudpingWhat 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 | $0.00769 | $0.00769 |
| Opus 5 | $0.00385 | $0.00385 |
| Sonnet 5 | $0.00154 | $0.00154 |
| Haiku 4.5 | $0.00077 | $0.00077 |
Grade A, and why
cloudping 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 2d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CloudPing — Agent Instructions
Project Overview
CloudPing is a distributed network diagnostic platform providing ping, traceroute, TCP ping, DNS probe, and HTTP probe via a hub-agent architecture.
- Hub: Central coordinator (
cmd/globalping+pkg/hub), listens :8080 (agent registration), :8082 (public API) - Agent: Edge nodes (
cmd/globalping agent), connect to hub via QUIC-over-mTLS - Web: React/TypeScript frontend (
web/), visualizes latency and routes - Bot: Telegram bot interface (
cmd/globalping bot), supports /ping, /traceroute, /probe - Workers: Background job processors (
workers/email/)
Technology Stack
- Backend: Go 1.25,
github.com/quic-go/quic-go,github.com/gorilla/websocket,github.com/golang-jwt/jwt/v5 - Frontend: TypeScript, React (Vite-based, inferred from
web/package.json) - Protocol: QUIC for hub-agent control; WebSocket for real-time frontend updates
- Auth: JWT for public API; mTLS (custom CA) for hub-agent
- Metrics: Prometheus
- Deployment: Docker + Docker Compose; Cloudflare Tunnel support
Critical Architecture Rules
- Hub-agent communication must use QUIC. Do not suggest falling back to raw TCP or HTTP polling for control messages.
- The mTLS certificate pairs are dual-use (server-auth + client-auth). Do not generate separate client certs unless explicitly requested.
- DNS probes support UDP, TCP, DoT (RFC 7858), and DoH (RFC 8484). Prefer DoH only when user explicitly asks for "secure DNS."
- All probe results stream back via WebSocket to the frontend. The polling fallback in
web/is deprecated; do not add new polling logic.
Code Conventions
Go
- Use
github.com/alecthomas/kongfor CLI flag parsing (already ingo.mod) - Prometheus metrics must use
cloudping_prefix - Error wrapping: use
fmt.Errorf("...: %w", err)consistently - Context cancellation: respect
ctxin all QUIC and WebSocket handlers
Frontend (TypeScript)
- Keep latency visualization canvas-based (using
tdewolff/canvasGo-side rendering or raw Canvas API client-side — checkweb/for current pattern) - The stargazer count badge in header is fetched client-side from GitHub API; cache aggressively
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.
- 2d ago First seen · 58 lines · 769 tokens per session scan A 1f5ec6db2e69
cloudping AGENTS.md is an instructions file published in the GitHub repository internetworklab/cloudping (25 stars, last pushed 2mo ago), licensed MIT. It adds 769 tokens to every session, about $0.0038 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
ftr CLAUDE.md
Instructions for dweekly/ftr, covering claude.md, project overview, build & test commands, git hooks (required) and compliance & release scripts.
pygase AGENTS.md
Instructions for sbischoff-ai/pygase, covering agents.md, architecture map (quick orientation), canonical uv commands, fast path vs full validation and testing conventions.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).