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/zentinelproxy/zentinel/agents-mdgit clone --depth 1 https://github.com/zentinelproxy/zentinelWrote 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/zentinelproxy/zentinel/agents-md)<a href="https://agentmods.dev/instructions/zentinelproxy/zentinel/agents-md"><img src="https://agentmods.dev/badge/instructions/zentinelproxy/zentinel/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 | $0.02253 | $0.02253 |
| Opus 5 | $0.01126 | $0.01126 |
| Sonnet 5 | $0.00451 | $0.00451 |
| Haiku 4.5 | $0.00225 | $0.00225 |
Grade A, and why
zentinel 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.
How it starts
The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zentinel
Security-first reverse proxy built to guard the free web.
Zentinel is an open-source, high-performance reverse proxy built on Cloudflare's Pingora framework. It emphasizes predictability, transparency, and operational simplicity—infrastructure that lets operators sleep.
Philosophy (North Star)
Every contribution must align with the Manifesto:
- Infrastructure should be calm — No surprises. Clear limits, predictable timeouts, explainable failure modes.
- Security must be explicit — No magic, no implied policy. Every decision visible and traceable.
- The edge is a boundary, not a battleground — Step in only when necessary, proportionally.
- Complexity must be isolated — Core dataplane stays small. Complex logic lives in external agents.
- The web is a commons — No vendor lock-in, no hidden control planes. Code is readable, forkable, modifiable.
- Production correctness beats feature breadth — Boring reliability over shiny features.
Before adding anything, ask:
- Does this introduce ambiguity?
- Can this fail loudly and safely?
- Will this make someone's on-call worse?
Architecture
┌─────────────────────────────────────────────────────────────────────┐
│ Zentinel Proxy │
│ ┌─────────────────────────────────────────────────────────────────┐│
│ │ Pingora Foundation ││
│ │ (async I/O, connection pooling, TLS, HTTP/1.1 & HTTP/2) ││
│ └─────────────────────────────────────────────────────────────────┘│
│ ┌──────────┐ ┌──────────┐ ┌──────────┐ ┌──────────┐ ┌────────────┐│
│ │ Routing │ │ Rate │ │ Cache │ │ Filters │ │ Agent ││
│ │ Engine │ │ Limiting │ │ Layer │ │ Chain │ │ Manager ││
│ └──────────┘ └──────────┘ └──────────┘ └──────────┘ └─────┬──────┘│
└────────────────────────────────────────────────────────────┼────────┘
│
┌────────────────────────────────────────┼────────┐
│ External Agents │ │
│ ┌─────────┐ ┌─────────┐ ┌─────────┐ │ │
│ │ WAF │ │ Auth │ │ Rate │ │◄───────┘
│ │ Agent │ │ Agent │ │ Limit │ │
│ └─────────┘ └─────────┘ └─────────┘ │
└───────────────────────────────────────────────────┘
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 · 249 lines · 2,253 tokens per session scan A dea9082557ee
zentinel AGENTS.md is an instructions file published in the GitHub repository zentinelproxy/zentinel (107 stars, last pushed today), licensed Apache-2.0. It adds 2,253 tokens to every session, about $0.0113 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
plano CLAUDE.md
Instructions for katanemo/plano, covering claude.md, build & test commands, rust — wasm plugins (must target wasm32-wasip1), rust — brightstaff binary (native target) and rust — tests, format, lint.
casbin-gateway CLAUDE.md
Claude Code instructions for apache/casbin-gateway, covering claude.md and code style.
bifrost AGENTS.md
Instructions for bifrost-proxy/bifrost, covering bifrost 项目开发规则, 执行心法, 执行模式与完成定义, 任务模式判定 and 变更类型与验证路由（先判定，后执行）.
mcp-proxy AGENTS.md
Instructions for joshrotenberg/mcp-proxy, covering agents.md, project structure, architecture, middleware stack ordering and key design pattern: error = infallible.
rustunnel CLAUDE.md
Claude Code instructions for joaoh82/rustunnel, covering claude.md, what is rustunnel, parent project, how i fit in and common commands.
rustunnel AGENTS.md
AGENTS.md instructions for joaoh82/rustunnel, covering agents.md, using rustunnel as a tool (expose local services), one-time setup the user must do and what you can do (mcp tools).