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.
npx agentmods add instructions/ekbatan-io/ekbatan/agents-mdgit clone --depth 1 https://github.com/ekbatan-io/ekbatanWrote 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.
[](https://agentmods.dev/instructions/ekbatan-io/ekbatan/agents-md)<a href="https://agentmods.dev/instructions/ekbatan-io/ekbatan/agents-md"><img src="https://agentmods.dev/badge/instructions/ekbatan-io/ekbatan/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.18130 | $0.18130 |
| Opus 5 | $0.09065 | $0.09065 |
| Sonnet 5 | $0.03626 | $0.03626 |
| Haiku 4.5 | $0.01813 | $0.01813 |
Grade A, and why
ekbatan 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 5d 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.
var customerThread = Thread.startVirtualThread(() -> customerService.fetch(params.customerId())); How it starts
The opening of the file, as written. The whole thing — 1,074 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agents Guide
This document provides detailed architectural context for AI agents working on the Ekbatan codebase.
Project Overview
Ekbatan is a Java persistence and action framework built as an alternative to Spring Data. It is a library, not a standalone application. Its central idea is that in most business applications, you don't just want to save data — you want to save what happened alongside the data itself, atomically, so that the database always tells a complete and consistent story.
The framework is structured around the concept of an Action — a unit of business work. An Action doesn't write anything to the database directly. Instead, it declares its intent: what should be created, what should be updated. These declarations accumulate in an ActionPlan — a staging area that holds all planned changes without touching the database. Only after the action's logic completes successfully does the ActionExecutor step in, open a single database transaction, and flush everything at once: the domain objects to their tables, and the event records to the eventlog schema. If any part fails, nothing is written. This all-or-nothing guarantee means the eventlog.events table naturally becomes a reliable outbox — a stream of committed business facts that can be tailed by a CDC connector or polled and forwarded to Kafka, Pulsar, or any message broker, enabling event-driven architectures without dual-write problems.
The framework draws a deliberate line between two kinds of persistent objects. A Model is a domain aggregate whose changes matter — every mutation produces a ModelEvent that gets persisted in the eventlog alongside the action that caused it. You extend Model when downstream systems need to know what happened: a wallet was created, money was deposited, an order was shipped. An Entity is simpler — it gets persisted and version-tracked, but its changes are not recorded as events. You extend Entity for supporting data where the history of individual mutations is irrelevant: lookup tables, configuration records, auxiliary references that participate in an action but don't need their own event trail.
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.
- 5d ago First seen · 1,074 lines · 18,130 tokens per session scan A 572bf7214846
ekbatan AGENTS.md is an instructions file published in the GitHub repository ekbatan-io/ekbatan (20 stars, last pushed today), licensed Apache-2.0. It adds 18,130 tokens to every session, about $0.0907 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.
Other instructions, from other repositories
atmosphere AGENTS.md
AGENTS.md instructions for Atmosphere/atmosphere, covering build system: maven, commands, module build, build only atmosphere-runtime (cpr) and build only spring-boot-starter.
liteflow CLAUDE.md
Instructions for dromara/liteflow, covering claude.md, 概述, 命令, 构建 and 构建整个项目(模块集由 jdk 版本自动选择 —— 见下方说明).
BitcoinAddressFinder CLAUDE.md
Claude Code instructions for bernardladenthin/BitcoinAddressFinder, covering claude.md — bitcoinaddressfinder, project overview, build system, common commands and compile only.
traverse AGENTS.md
AGENTS.md instructions for traverse-framework/traverse, covering traverse — agent coordination, agent coordination, 1. check for claude code claim, 2. check for claude code branch and 3. claim the ticket (only if pre-flight passes).
camunda load-tests.instructions.md
Instructions for camunda/camunda, covering load test review guidelines, required review checks, what gets backported, documentation and scheduled release load tests.
nano AGENTS.md
AGENTS.md instructions for NanoNative/nano, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.