plugin-development

plugin-development is a cursor rule for Cursor from higress-group/higress. It costs 0 tokens per session (809 once invoked), scanned A, original, Apache-2.0.

Rules for creating or materially changing Higress WebAssembly or Go-based gateway plugins. They cover repository guidance, approval requirements, implementation tasks, and verification evidence.

In plain words
What is it for?
Use them when developing or changing a WASM or golang-filter plugin in Higress. They guide planning, implementation, testing, and the evidence needed for review.
Why use it?
They provide a consistent contribution process and reduce the risk of shipping plugins without the required design approval or tests. They also clarify that the approved issue-spec design is the authoritative plan.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions AGENTS.md.

Good fit Use them when developing or changing a WASM or golang-filter plugin in Higress. They guide planning, implementation, testing, and the evidence needed for review.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/higress-group/higress/plugin-development
About the project

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.

higress-group/higress · 9,569 stars · on GitHub · higress.ai

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.

Clone the repo
git clone --depth 1 https://github.com/higress-group/higress

Made for: Cursor.

Wrote 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.

agentmods badge for plugin-development

README.md
[![agentmods](https://agentmods.dev/badge/rules/higress-group/higress/plugin-development/github.svg)](https://agentmods.dev/rules/higress-group/higress/plugin-development)
Your own site
<a href="https://agentmods.dev/rules/higress-group/higress/plugin-development"><img src="https://agentmods.dev/badge/rules/higress-group/higress/plugin-development/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for plugin-development

Your own site · 80×15
<a href="https://agentmods.dev/rules/higress-group/higress/plugin-development"><img src="https://agentmods.dev/badge/rules/higress-group/higress/plugin-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 809 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.00809
Opus 5.5 $0.00000 $0.00324
Sonnet 5.5 $0.00000 $0.00162
Haiku 4.5 $0.00000 $0.00081

Measured 1mo ago against content hash 62fdcb379e69, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

plugin-development 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 1mo 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.

.cursor/rules/plugin-development.mdc · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plugin Development Standards

These rules apply when creating or materially changing a Wasm or golang-filter plugin. Follow the repository-wide build and test guidance in AGENTS.md and the contributor guide.

Agent participation and issue-spec gate

Before implementation, determine whether an AI or coding agent will materially participate under the agent-assisted contribution policy. When material participation applies:

  • enter the Higress issue-spec workflow before implementation begins;
  • do not begin implementation until a Higress maintainer has approved the Proposal Issue and Design Issue;
  • 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
  • complete the applicable implementation and verification TASKs with commands, results, evidence links, and hashes before asking maintainers to accept the verification or review.

The maintainer-approved issue-spec Design Issue is the authoritative design carrier. No plugin-local design/ directory, design document, or AI prompt file is required for this gate, and none should be created or required as a substitute for the approved Design Issue.

Disclose the prompts or instructions given to the agent and provide an AI-assisted work summary in the pull request template, with secrets and sensitive data removed. Human-only work is outside this agent gate. The narrow trivial-edit exception is defined in the canonical policy and must be declared when used. A canonical-repository maintainer or administrator may use the verified maintainer/administrator exception only after completing the canonical policy's authenticated gh identity and collaborator-permission checks and recording the login, returned role_name of maintain or admin, and bypass rationale in the PR. The current PR author must match the verified login. This must include a positive attestation that both GH_TOKEN and GITHUB_TOKEN were unset for every verification command and fail closed on a missing, failed, or mismatched check; the accepting or merging maintainer independently validates current live evidence with token overrides unset. This does not waive bug-fix runtime verification.

Read the full file on GitHub · 80 lines

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. 1mo ago First seen · 80 lines · 0 tokens per session scan A 62fdcb379e69

Subscribe to this mod's changes

plugin-development is a cursor rule published in the GitHub repository higress-group/higress (9,569 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 809 tokens. 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.