LSP-Examples: Instructions file for Codex

AGENTS.md

LSP-Examples AGENTS.md is an instructions file for Codex, OpenCode from RealTimeLogic/LSP-Examples. It costs 4,937 tokens per session, scanned A, original, MIT.

Repository instructions for independent examples using the Barracuda App Server ecosystem. BAS is an embedded C/C++ web server, Mako Server is its standalone runtime, and Lua Server Pages are web pages that run Lua on the server.

In plain words
What is it for?
Use them before analyzing, editing, generating, or testing an example, especially when preparing the required references and identifying the correct application root.
Why use it?
They prevent work from starting with missing reference material or the wrong example, runtime, or undocumented API.

Instructions file for CodexOpenCode

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

This is RealTimeLogic/LSP-Examples's own configuration. It tells Codex and OpenCode how to work on LSP-Examples 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 LSP-Examples configures →

Reuse

Borrowing it

Nothing to install: this file belongs to RealTimeLogic/LSP-Examples. 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/RealTimeLogic/LSP-Examples/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/RealTimeLogic/LSP-Examples

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 LSP-Examples AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/realtimelogic/lsp-examples/agents-md"><img src="https://agentmods.dev/badge/instructions/realtimelogic/lsp-examples/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,937 This file is loaded in full into every session.
When invoked 4,937 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 $0.04937 $0.04937
Opus 5.5 $0.01975 $0.01975
Sonnet 5.5 $0.00987 $0.00987
Haiku 4.5 $0.00494 $0.00494

Measured 2mo ago against content hash b83cc125f1f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

LSP-Examples 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 · 449 lines

How it starts

The opening of the file, as written. The whole thing — 449 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - BAS, Mako, and Xedge Examples

Purpose

This repository contains independent examples for the Barracuda App Server (BAS) ecosystem:

  • BAS is the embedded C/C++ web and application server library.
  • Mako Server is a standalone BAS runtime for desktop, server, and embedded Linux development and deployment.
  • Xedge is a BAS-powered application environment commonly embedded in a product or firmware image.
  • Xedge32 is the ESP32 edition of Xedge and adds ESP32 hardware APIs.
  • LSP means Lua Server Pages: HTML resources that execute server-side Lua.

Examples are independent teaching applications, not one monolithic program. Keep changes scoped to the selected example and runtime.

Non-Negotiable Start Gate

Do not analyze, edit, generate, or test repository files until both of these steps are complete:

  1. Download and read all 11 mandatory references and skills listed below.
  2. Identify the selected example, its runnable app root, its target runtime, and its local instructions.

Do not continue with a partial reference set or guess an undocumented API.

Mandatory Reference Bootstrap

At the beginning of a task, create ./.agents/reference/rtl/ relative to this file and download or refresh every file in the two tables below. Save each file using its listed local filename. Verify that every response succeeded and every file is non-empty; an HTML error page is not a valid reference download.

Create or update ./.agents/reference/rtl/manifest.md with:

  • download date;
  • source URL;
  • local filename;
  • any download or validation failure.

Read all downloaded references and skills before making changes. The task-specific guidance later in this file determines which skills are most important for the implementation; it does not make the other downloads optional.

If Downloading Fails

If network or filesystem restrictions block a download:

  1. Ask for the elevated network or filesystem permissions required to download and save the files.
  2. Retry after permission is granted.
  3. If permission is unavailable or downloading still fails, stop before modifying the repository.
  4. Give the user a copy-ready list of every missing file. Each item must contain the clickable download link and exact destination path under ./.agents/reference/rtl/.
  5. Ask the user to provide the files locally and resume only after all 11 files are accessible and non-empty.

Read the full file on GitHub · 449 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 · 449 lines · 4,937 tokens per session scan A b83cc125f1f1

Subscribe to this mod's changes

LSP-Examples AGENTS.md is an instructions file published in the GitHub repository RealTimeLogic/LSP-Examples (43 stars, last pushed 21d ago), licensed MIT. It adds 4,937 tokens to every session, about $0.0197 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.

Related

LSP-Examples AGENTS.md compared with instructions from other repositories

LSP-Examples AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
LSP-Examples AGENTS.mdRealTimeLogic/LSP-ExamplesInstructions file4321d agoMITA4,937Codex, 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