Higress is a cloud-native API gateway built on Istio and Envoy that routes and manages APIs and can be extended with WebAssembly plugins. It is used to manage APIs for AI models and MCP servers as well as general services, and the catalogue entries provide agent workflows and integrations for operating it.
Borrowing it
Nothing to install: this file belongs to higress-group/higress. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/higress-group/higress/main/AGENTS.mdgit clone --depth 1 https://github.com/higress-group/higressWrote 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/higress-group/higress/agents-md)<a href="https://agentmods.dev/instructions/higress-group/higress/agents-md"><img src="https://agentmods.dev/badge/instructions/higress-group/higress/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 5.1 | $0.02905 | $0.02905 |
| Opus 5 | $0.01452 | $0.01452 |
| Sonnet 5 | $0.00581 | $0.00581 |
| Haiku 4.5 | $0.00291 | $0.00291 |
Grade A, and why
higress 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 7d 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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI agents working in this repository.
Higress is a cloud-native API gateway built on Istio and Envoy. The control
plane extends Istio/pilot (Go); the data plane is Envoy extended with WASM
plugins (Go/Rust/C++/AssemblyScript) and a Go-based golang-filter. It supports
Ingress/Gateway API and ships a rich plugin ecosystem (including AI gateway
plugins).
Mandatory issue-spec gate for agent-assisted changes
Before substantive implementation, determine whether an AI or coding agent is materially participating under the agent-assisted contribution policy. For every contribution to which that policy applies:
- do not begin implementation until a Higress maintainer has approved both the Proposal Issue and Design Issue; an issue-spec status or agent assertion is not maintainer approval;
- implement only through TASKs authorized by the approved Design and preserve traceability to the applicable SPECs;
- ensure the Design contains a concrete Verification Plan before verification begins; and
- create and complete the corresponding verification TASKs with exact commands, results, evidence links, and hashes before claiming success or asking maintainers to accept verification or review.
Declare agent participation in the PR template. The policy excludes human-only
work. Small documentation-only corrections limited to spelling, punctuation,
whitespace, or formatting (such as typo adjustments) may skip the issue-spec
workflow when they involve no substantive choice or behavioral effect.
Agent-assisted bug fixes and material feature work must still follow this gate.
An authenticated gh user with canonical-repository role_name of maintain
or admin may use the verified maintainer/administrator exception documented
in the canonical policy. Before bypassing the gate, run the documented gh
identity and collaborator-permission checks, record the login, returned
role_name, actual PR author, and rationale in the PR, and still disclose agent
participation. The PR author must match the verified login and the PR must attest
that GH_TOKEN and GITHUB_TOKEN were unset for every verification command;
any failed or mismatched check disqualifies the exception. Select the matching
verified-exception status in the PR template. The accepting or merging maintainer
must independently validate current live evidence with token overrides unset.
This exception never waives bug-fix runtime verification.
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.
- 7d ago First seen · 204 lines · 2,905 tokens per session scan A f94959032edc
higress AGENTS.md is an instructions file published in the GitHub repository higress-group/higress (9,305 stars, last pushed yesterday), licensed Apache-2.0. It adds 2,905 tokens to every session, about $0.0145 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
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.
vscode buildNext.instructions.md
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
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.