agentmods.dev

kotlinx-schema: Instructions file for Codex

AGENTS.md

kotlinx-schema AGENTS.md is an instructions file for Codex, OpenCode from Kotlin/kotlinx-schema. It costs 1,581 tokens per session, scanned A, original, Apache-2.0.

Project instructions for a Kotlin library that creates JSON Schema and function descriptions for AI tools from Kotlin code. They explain the project layout, supported generation methods, build commands, tests, public API checks, and documentation examples.

In plain words
What is it for?
Use them when changing Kotlin modules, schema generation, public APIs, tests, Gradle builds, or README code examples. KMP means Kotlin Multiplatform, a way to share code across platforms.
Why use it?
They tell coding agents which checks to run and which generated files must be updated after API or documentation changes. This avoids broken builds, stale API records, and failing documentation checks.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is Kotlin/kotlinx-schema's own configuration. It tells Codex and OpenCode how to work on kotlinx-schema itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything kotlinx-schema configures →

not rated 139repo 3d ago A scan 1,581 tokens original Apache-2.0
View source ↗ Kotlin/kotlinx-schema kotlin.github.io
Reuse

Borrowing it

Nothing to install: this file belongs to Kotlin/kotlinx-schema. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Kotlin/kotlinx-schema/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Kotlin/kotlinx-schema

Made for: Codex, OpenCode.

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 kotlinx-schema AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kotlin/kotlinx-schema/agents-md/github.svg)](https://agentmods.dev/instructions/kotlin/kotlinx-schema/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/kotlin/kotlinx-schema/agents-md"><img src="https://agentmods.dev/badge/instructions/kotlin/kotlinx-schema/agents-md/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 kotlinx-schema AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/kotlin/kotlinx-schema/agents-md"><img src="https://agentmods.dev/badge/instructions/kotlin/kotlinx-schema/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,581 This file is loaded in full into every session.
When invoked 1,581 The same file — it is already loaded in full.
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 $0.01581 $0.01581
Opus 5.5 $0.00632 $0.00632
Sonnet 5.5 $0.00316 $0.00316
Haiku 4.5 $0.00158 $0.00158

Measured 2mo ago against content hash c0efe90ac874, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

kotlinx-schema 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 2mo 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 · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file provides guidance to coding agents when working with code in this repository.

Project

Kotlin library that generates JSON Schema (Draft 2020-12) and LLM function-calling schemas from Kotlin code. Three generation modes — KSP (compile-time, multiplatform), reflection (JVM runtime), and kotlinx.serialization SerialDescriptor (multiplatform runtime) — all funnel through a shared IR (TypeGraph).

Build Commands

./gradlew build                          # Full build + tests (matches CI)
./gradlew checkKotlinAbi                 # ABI check — fails if api/*.api is stale
./gradlew updateKotlinAbi                # Regenerate ABI dump after public API changes; commit the diff
./gradlew :docs:knitCheck --no-configuration-cache   # Validate README/docs snippets

README snippets in <!--- INCLUDE --> / <!--- KNIT example-knit-readme-NN.kt --> blocks are extracted to .kt files under docs/ and compiled by knit — if you touch them, knitCheck will fail until you regenerate.

Single test (prefer jvmTest on KMP modules):

./gradlew :<module>:jvmTest --tests "FQN.TestClass.test name with backticks"
./gradlew :ksp-integration-tests:test    # KSP end-to-end (no Gradle plugin)
./gradlew :ksp-integration-tests:build   # trigger KSP codegen → build/generated/ksp/

Gradle plugin integration tests (separate composite build via includeBuild(), only sees the plugin after publication):

./gradlew publishPluginAndSync           # publish plugin to build/project-repo; reload IDE after
./gradlew testGradlePlugin               # publish + run :gradle-plugin-integration-tests:allTests

Module Structure

kotlinx-schema-annotations         Runtime annotations (@Schema, @Description, @SchemaIgnore)
kotlinx-schema-json                JSON Schema Draft 2020-12 type-safe models + DSL (standalone)
kotlinx-schema-generator-core      IR (TypeGraph) + introspector/transformer interfaces
kotlinx-schema-generator-json      TypeGraph → JsonSchema / FunctionCallingSchema; reflection + serialization generators
kotlinx-schema-ksp                 KSP processor; uses generator-json
kotlinx-schema-ksp-gradle-plugin   Applies KSP, wires source sets
ksp-integration-tests              KSP end-to-end tests (no Gradle plugin)
gradle-plugin-integration-tests    Composite build that exercises the plugin as external users would

Read the full file on GitHub · 88 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. 2mo ago First seen · 88 lines · 1,581 tokens per session scan A c0efe90ac874

Subscribe to this mod's changes

kotlinx-schema AGENTS.md is an instructions file published in the GitHub repository Kotlin/kotlinx-schema (139 stars, last pushed 3d ago), licensed Apache-2.0. It adds 1,581 tokens to every session, about $0.0063 per session on Opus 5.5. 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.

Code GenerationJSON Schemakotlinkotlin-symbol-processingkotlin-symbol-processor
Related

kotlinx-schema AGENTS.md compared with instructions from other repositories

kotlinx-schema AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
kotlinx-schema AGENTS.mdKotlin/kotlinx-schemaInstructions file1393d agoApache-2.0A1,581Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot