conductor AGENTS.md

A contributor guide for Conductor, an open-source distributed workflow system for microservices. It explains the Java version, Gradle build commands, testing, formatting, and the project's pluggable design.

In plain words
What is it for?
Use it when building or testing Conductor, formatting Java changes, choosing supported Java documentation wording, or adding features that fit its modular architecture.
Why use it?
It helps coding agents set up the project correctly and keep changes consistent with its build and style requirements.

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

Made for: Codex, OpenCode.

Per session 2,100 This file is loaded in full into every session.
When invoked 2,100 The same file — it is already loaded in full.
Security scan A 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 $0.02100 $0.02100
Opus 5 $0.01050 $0.01050
Sonnet 5 $0.00420 $0.00420
Haiku 4.5 $0.00210 $0.00210

Measured 2d ago against content hash f1d8e7ad34f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

conductor AGENTS.md scanned grade A 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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

This matters because plausible-looking docs can be silently wrong. Concretely: a curl equivalent for `conductor workflow start --sync` was once written as `POST /api/workflow/{name}/run` — an endpoint that does not exist
AGENTS.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Instructions for AI coding agents working on the Conductor codebase.

Project Overview

Conductor is an open-source, distributed workflow orchestration engine designed for microservices. It uses a pluggable architecture with interface-based abstractions for persistence, queuing, and indexing. The project is built with Java 21 and uses Gradle as the build system.

Setup Commands

Command Description
./gradlew build Build the entire project
./gradlew test Run all tests
./gradlew :module-name:test Run tests for a specific module
./gradlew spotlessApply Apply code formatting
./gradlew clean build Clean and rebuild

Important: Always run ./gradlew spotlessApply after making code changes to ensure consistent formatting.

Java Version References

Never link to a specific Java distribution (e.g., Adoptium, Temurin, OpenJDK.org, Amazon Corretto) in docs, READMEs, or comments. Just say "Java 21+" and let users install it however they prefer.

Code Style

  • Use the Spotless plugin for uniform code formatting—always run before committing
  • Conductor is pluggable: when introducing new concepts, always use an interface-based approach
  • DAO interfaces MUST be defined in the core module
  • Implementation classes go in their respective persistence modules (e.g., postgres-persistence, redis-persistence)
  • Follow existing patterns in the codebase for consistency
  • Do not use emojis such as ✅ in the code, logs, or comments. Keep comments professionals
  • When adding new logic, comment the algorithm, design etc.

Architecture Guidelines

Module Structure

  • core: Contains interfaces, domain models, and core business logic
  • persistence modules: Implementations of DAO interfaces (postgres, redis, mysql, etc.)
  • server: Spring Boot application that brings everything together
  • client: SDK for interacting with Conductor
  • ui: React-based user interface

Read the full file on GitHub · 178 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 · 178 lines · 2,100 tokens per session scan A f1d8e7ad34f7

Subscribe to this mod's changes

conductor AGENTS.md is an instructions file published in the GitHub repository conductor-oss/conductor (32,161 stars, last pushed today), licensed Apache-2.0. It adds 2,100 tokens to every session, about $0.0105 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.