agentmods.dev

superplane AGENTS.md

A repository guide for coding agents and contributors working on SuperPlane, an open-source automation engine for engineering workflows. It explains the project, its folders, required tools, and commands for building, testing, and checking changes.

In plain words
What is it for?
Use it when making changes in the SuperPlane repository, especially for setup, build, test, lint, and code-location questions. UI work may require the additional guides it names.
Why use it?
It gives contributors the project-specific rules they need before editing code. This reduces mistakes such as changing the wrong files, using the wrong setup, or writing incorrect user-facing text.

Instructions file for CodexOpenCode

5.6k yesterday B scan 3,898 tokens original Apache-2.0
View the source file superplanehq/superplane
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/superplanehq/superplane/agents-md
Clone the repo
git clone --depth 1 https://github.com/superplanehq/superplane

Made for: Codex, OpenCode.

Per session 3,898 This file is loaded in full into every session.
When invoked 3,898 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.03898 $0.03898
Opus 5 $0.01949 $0.01949
Sonnet 5 $0.00780 $0.00780
Haiku 4.5 $0.00390 $0.00390

Measured yesterday against content hash 8567951467a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

superplane AGENTS.md scanned grade B with 1 finding 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

`sudo dockerd &>/tmp/dockerd.log &` — wait ~3-4 seconds before issuing Docker
AGENTS.md · 319 lines

How it starts

The opening of the file, as written. The whole thing — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Guidance for AI coding agents and human contributors working in this repository. Read this top-to-bottom: what the project is, how to set it up, how to build and test, the conventions to follow, what not to touch, and how to submit changes. For UI-specific work, also read web_src/AGENTS.md, .agents/skills/ui-copy/SKILL.md, and .agents/skills/simplified-technical-english/SKILL.md.

Project Overview

SuperPlane is an open-source automation engine for AI-driven engineering. It orchestrates workflows across the tools teams already use (Git, LLMs, CI/CD, observability, incident, and infrastructure tools) with durable execution, approvals, and an operational UI.

  • Backend: Go, exposing a gRPC API with a REST/OpenAPI gateway.
  • Frontend: TypeScript + React, built with Vite.
  • Infrastructure: PostgreSQL (state) and RabbitMQ (messaging), run via Docker.
  • The application name is SuperPlane (not "Superplane") in all user-facing text.

Repository Layout

  • cmd/ — Go entrypoints (server, workers, CLI).
  • pkg/ — Go application code. Notable packages:
    • pkg/grpc/actions — gRPC API implementation.
    • pkg/models — database models.
    • pkg/workers — background workers.
    • pkg/integrations/<integration>/ — integration component implementations.
  • web_src/ — TypeScript/React frontend (Vite). UI component mappers live in web_src/src/pages/app/mappers/<integration>/.
  • protos/ — protobuf definitions for the API.
  • db/ — database structure and migrations.
  • scripts/ — codegen, DB, and CI helper scripts.
  • test/ — backend and end-to-end tests.
  • docs/ — Markdown documentation (see docs/contributing/).
  • Makefile — the entrypoint for all common tasks.

Prerequisites & Setup

The development environment is entirely Docker-based: build, lint, test, and run commands execute inside containers via docker compose. You do not need Go or Node installed on the host, only Docker.

Read the full file on GitHub · 319 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. yesterday First seen · 319 lines · 3,898 tokens per session scan B 8567951467a5

Subscribe to this mod's changes

superplane AGENTS.md is an instructions file published in the GitHub repository superplanehq/superplane (5,633 stars, last pushed yesterday), licensed Apache-2.0. It adds 3,898 tokens to every session, about $0.0195 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Code reviewGit and workflowTestingcontrol-planeevent-drivenkubernetesrelease-automationself-hosted
Related

Other instructions, from other repositories

meshery AGENTS.md

Instructions for meshery/meshery, covering project overview, repository structure, identifier naming conventions — mandatory, per-layer canonical forms and forbidden (must not).

meshery/meshery · 6,682 tokens

meshery copilot-instructions.md

Instructions for meshery/meshery, covering copilot instructions for meshery, project overview, repository structure, tech stack and backend (server & cli).

meshery/meshery · 972 tokens

nora CLAUDE.md

Instructions for solomon2773/nora, covering claude.md, what this repo is, development commands, docker compose (primary path) and per-service dev (without docker).

solomon2773/nora · 2,859 tokens

asya GEMINI.md

Instructions for deliveryhero/asya, a project described as: 🎭 Distributed Actor Mesh on K8s for AI Agents.

deliveryhero/asya · 10 tokens

asya AGENTS.md

Instructions for deliveryhero/asya, covering agents.md, project overview, quick reference, testing strategy and envelope protocol.

deliveryhero/asya · 4,405 tokens

meshery CLAUDE.md

Instructions for meshery/meshery, a project described as: Meshery, the cloud native manager.

meshery/meshery · 5 tokens