infinispan: Instructions file for Codex

AGENTS.md

infinispan AGENTS.md is an instructions file for Codex, OpenCode from infinispan/infinispan. It costs 486 tokens per session, scanned A, original, Apache-2.0.

A set of project instructions for working on Infinispan, a Java data store and cache that runs across multiple machines. It covers coding, testing, configuration, documentation, issue creation, and pull request review.

In plain words
What is it for?
Use it when changing Infinispan code, tests, configuration, documentation, issues, or pull requests so the work follows the repository's instructions.
Why use it?
It gives a coding agent the project's conventions and special rules instead of leaving it to guess how changes should be made. This helps protect compatibility in a long-lived open-source project.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions Claude Code; mentions AGENTS.md.

This is infinispan/infinispan's own configuration. It tells Codex and OpenCode how to work on infinispan 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 infinispan configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is for skill in ../../.ai-skills/*/; do.

About the project

Infinispan is an open-source in-memory database and distributed data grid that stores and processes key-value data across scalable clusters, either as a cache or persistent store. Developers use it for high-availability data storage and for holding data ranging from Java objects to plain text. The catalogue entries provide rules and instructions for working with Infinispan.

infinispan/infinispan · 1,359 stars · on GitHub · infinispan.org

Reuse

Borrowing it

Nothing to install: this file belongs to infinispan/infinispan. 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/infinispan/infinispan/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/infinispan/infinispan

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 infinispan AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/infinispan/infinispan/agents-md"><img src="https://agentmods.dev/badge/instructions/infinispan/infinispan/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 486 This file is loaded in full into every session.
When invoked 486 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 $0.00486 $0.00486
Opus 5.5 $0.00194 $0.00194
Sonnet 5.5 $0.00097 $0.00097
Haiku 4.5 $0.00049 $0.00049

Measured 17d ago against content hash 338dd6d6524f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

infinispan 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 17d 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 · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Context: Infinispan

Infinispan is a distributed in-memory key/value data store and cache, written in Java.

Shared guidelines

  • Use the project's established patterns and terminology. When in doubt, follow the conventions of the module you are working in.
  • Prefer clarity over cleverness. This is a long-lived open-source project with many contributors.
  • Be aware of backward compatibility implications — Infinispan supports rolling upgrades and client/server version mismatches.

Coding instructions

When planning and writing code, read and follow the instructions in AI-CODE.md.

Testing instructions

When writing or modifying tests, read and follow the instructions in AI-TEST.md.

Configuration change instructions

When adding or modifying configuration attributes, read and follow the instructions in AI-CONFIG.md.

Documentation instructions

When writing or editing documentation, read and follow the instructions in documentation/AI-CODE.md.

Issue creation instructions

When creating GitHub issues, read and follow the instructions in AI-ISSUES.md.

Pull request review instructions

When reviewing PRs, read and follow the instructions in REVIEW.md.

AI skills

Reusable skills (slash commands) are stored in the .ai-skills/ directory, committed to the repository. Each agent tool has its own skills directory (e.g. .claude/skills/ for Claude Code). To make the shared skills available, symlink each skill into your agent's skills directory:

# Claude Code
cd .claude/skills
for skill in ../../.ai-skills/*/; do
  ln -sfn "$skill" "$(basename "$skill")"
done

Maintaining AI context files

When making changes that alter the project structure, module organization, build process, or architectural patterns, check whether the relevant AI context files need updating: AGENTS.md, AI-CODE.md, AI-TEST.md, AI-CONFIG.md, AI-ISSUES.md, REVIEW.md, documentation/AI-CODE.md, and any module-level AI-CODE.md files. The architecture documentation in documentation/src/main/asciidoc/titles/architecture/ should also be checked when internal architecture changes. Examples of changes that warrant updates: renaming or moving modules, adding new modules, changing build commands, introducing new frameworks or test patterns, modifying configuration architecture, or updating development conventions.

Read the full file on GitHub · 43 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. 17d ago Changed · +13 lines · +113 tokens per session 338dd6d6524f
  2. 1mo ago First seen · 30 lines · 373 tokens per session scan A fdc1fc6ffdfd

Subscribe to this mod's changes

infinispan AGENTS.md is an instructions file published in the GitHub repository infinispan/infinispan (1,359 stars, last pushed today), licensed Apache-2.0. It adds 486 tokens to every session, about $0.0019 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 2026-09-25.

Related

infinispan AGENTS.md compared with instructions from other repositories

infinispan AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
infinispan AGENTS.mdinfinispan/infinispanInstructions file1.4ktodayApache-2.0A486Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode