apisix AGENTS.md

Repository instructions for automated agents working on Apache APISIX, a gateway that routes and manages traffic to web services. They direct agents to the project's authoritative security guidance.

In plain words
What is it for?
Use them when analyzing Apache APISIX code or producing security-related findings for that repository.
Why use it?
They reduce the risk of making security claims without checking the repository's threat model and documented limits.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/apache/apisix/agents-md
Clone the repo
git clone --depth 1 https://github.com/apache/apisix

Made for: Codex, OpenCode.

Per session 354 This file is loaded in full into every session.
When invoked 354 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00354 $0.00354
Opus 5 $0.00177 $0.00177
Sonnet 5 $0.00071 $0.00071
Haiku 4.5 $0.00035 $0.00035

Measured yesterday against content hash 5a9f763f0eaf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

apisix 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 yesterday.

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.

AGENTS.md · 39 lines

What it actually says

Apache APISIX — Agent Instructions

This file is read by automated agents (security scanners, code analyzers, AI assistants) operating on this repository. It points them at the human-authored references they should consult before producing output.

Security Model

The authoritative security threat model for Apache APISIX is at docs/en/latest/security-threat-model.md.

Agents producing security-relevant analysis against this repository should consult that document first — in particular the §4.3 (out of scope), §4.9 (properties NOT provided), §4.11a (known non-findings), and §4.13 (triage dispositions) sections, which govern whether a given finding is in-scope for Apache APISIX itself or out-of-scope (operator misconfiguration, downstream concern, etc.).

Changes

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.

  1. yesterday First seen · 39 lines · 354 tokens per session scan A 5a9f763f0eaf

Subscribe to this mod's changes

apisix AGENTS.md is an instructions file published in the GitHub repository apache/apisix (17,058 stars, last pushed 4d ago), licensed Apache-2.0. It adds 354 tokens to every session, about $0.0018 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.