kiwi AGENTS.md

A repository guide for Kiwi, a multi-module Java and Angular application built in one shared codebase, called a monorepo. It documents the system layout and developer commands.

In plain words
What is it for?
Use it when changing Kiwi's Spring Boot backend, Angular frontend, BPMN modules, optional integrations, or OpenSpec change proposals.
Why use it?
It gives coding agents the project context needed to work in the right module, follow the repository's conventions, and use the correct build and run workflow.

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/xc404/kiwi/agents-md
Clone the repo
git clone --depth 1 https://github.com/xc404/kiwi

Made for: Codex, OpenCode.

Per session 1,656 This file is loaded in full into every session.
When invoked 1,656 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 $0.01656 $0.01656
Opus 5 $0.00828 $0.00828
Sonnet 5 $0.00331 $0.00331
Haiku 4.5 $0.00166 $0.00166

Measured 2d ago against content hash 1874619b49f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

kiwi 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 2d 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.

AGENTS.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Kiwi Codebase Guide

Architecture Overview

Maven multi-module monorepo: Java 25 + Spring Boot 4.0 backend (Operaton BPM engine embedded) + Angular 21 frontend.

kiwi-common/              # Shared entities, Mongo/MyBatis base classes
kiwi-bpmn/
  kiwi-bpmn-core/         # @ComponentDescription / @ComponentParameter annotations, variable mapping, job retry
  kiwi-bpmn-component/    # Official delegates (Shell, HTTP, MongoDB, JDBC, …) as Maven dependency; optional integrations as plugin JARs
  kiwi-bpmn-external-task/ # External Task abstraction
kiwi-admin/
  backend/                # com.kiwi.framework.* (infra) + com.kiwi.project.{system,bpm,ai,tools,monitor,notification}
  frontend/               # src/app/{core,layout,pages,shared,config,utils}; BPMN editor at pages/bpm
openspec/                 # Spec-driven change proposals (see OpenSpec Workflow below)

Developer Workflows

Backend (local dev):

# From repo root — compiles all upstream modules
mvn -pl kiwi-admin/backend -am compile -DskipTests
# Run Application with profiles: local,dev  (port 8000, H2 engine DB, MyBatis stdout)
# Working directory MUST be kiwi-admin/backend — optional plugin JARs are under plugins/

Core BPM components (kiwi-bpmn-component) are a Maven dependency on the backend classpath (classpath_*). Optional integrations (Kafka, S3, Slack, Payment, …) ship as slim shaded plugin JARs in kiwi-admin/backend/plugins/. Only when changing those plugin modules, rebuild and commit:

mvn -pl kiwi-admin/backend -am package -Pbuild-plugins -DskipTests

Copy application.example.ymlapplication-local.yml; fill MongoDB URI and kiwi.mongodb.init.admin-password.

Frontend:

cd kiwi-admin/frontend && npm install && npm start   # http://localhost:4201

environment.ts api.baseUrl must match the running backend port (8000 for dev profile, 8080 otherwise).

Full stack (Docker):

docker compose -f docker/docker-compose.yml up -d --build   # http://localhost:8080/kiwi-admin/

Read the full file on GitHub · 110 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. 2d ago First seen · 110 lines · 1,656 tokens per session scan A 1874619b49f6

Subscribe to this mod's changes

kiwi AGENTS.md is an instructions file published in the GitHub repository xc404/kiwi (7 stars, last pushed 8d ago), licensed MIT. It adds 1,656 tokens to every session, about $0.0083 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.

Related

Other instructions, from other repositories

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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.

openai/codex · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

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).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens