OpenSail AGENTS.md

OpenSail AGENTS.md is an instructions file for Codex, OpenCode from TesslateAI/OpenSail. It costs 9,646 tokens per session, scanned A, original, Apache-2.0.

Project-specific instructions for a coding agent working on TesslateAI/OpenSail, including its architecture, technology stack, documentation, and code paths.

In plain words
What is it for?
Use them when developing or fixing OpenSail, especially when navigating its documentation, deployment setup, or recurring infrastructure problems.
Why use it?
They give the agent background and working rules so changes fit the existing project and avoid breaking related systems. They also describe practices for Kubernetes, Docker, and non-blocking changes.

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/tesslateai/opensail/agents-md
Clone the repo
git clone --depth 1 https://github.com/TesslateAI/OpenSail

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 OpenSail AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tesslateai/opensail/agents-md.svg)](https://agentmods.dev/instructions/tesslateai/opensail/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/tesslateai/opensail/agents-md"><img src="https://agentmods.dev/badge/instructions/tesslateai/opensail/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 9,646 This file is loaded in full into every session.
When invoked 9,646 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.09646 $0.09646
Opus 5 $0.04823 $0.04823
Sonnet 5 $0.01929 $0.01929
Haiku 4.5 $0.00965 $0.00965

Measured 4d ago against content hash 772352e6be9e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

OpenSail 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 4d 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 · 900 lines

How it starts

The opening of the file, as written. The whole thing — 900 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior level coding agent. You will apply real world solutions to all the problems, fixing them in such a way where you do not cheat the solution, break existing functionality, and are scoped in. The solutions you write must be scalable and for the future, not fixing or hardcoding.

Always read through the docs/ to find items it is a knowledgegraph

Use subagents generously if you are doing bulk task items that have a small / atomic scope.

don't do conditional logic for k8s and docker implementation differences. try to keep it as similar as possible unless if a platform requires differeces. Prioritize the k8s (keep that logic more intact than docker. )

On windows use MSYS_NO_PATHCONV=1 while running kubectl or docker exec commands. The ECR IS <AWS_ACCOUNT_ID> not <AWS_ACCOUNT_ID>

CRITICAL -- ENSURE ALL CHANGES ARE NON-BLOCKING

Everything u do or write should be non-blocking so certain actions don't hold up other people on our software.

OpenSail

When I have an issue, fix it for the next time it happens in a general, scalable way. For example, if a container fails on startup, ensure all future container startups work 100%.

What is OpenSail?

AI-powered web application builder that lets users create, edit, deploy, and manage full-stack apps using natural language. Users describe what they want, an AI agent writes the code, and the platform handles containerized deployment.

Architecture Overview

┌─────────────────────────────────────────────────────────────┐
│                    OpenSail                                 │
├─────────────────────────────────────────────────────────────┤
│  Frontend (app/)           │   Orchestrator (orchestrator/) │
│  React + Vite + TypeScript │   FastAPI + Python             │
│  - Monaco Editor           │   - Auth (JWT/OAuth)           │
│  - Live Preview            │   - Project Management         │
│  - Chat UI                 │   - AI Agent System            │
│  - File Browser            │   - Container Orchestration    │
├─────────────────────────────────────────────────────────────┤
│  Redis                │  ARQ Worker                          │
│  - Pub/Sub + Streams  │  - Distributed agent execution       │
│  - Task queue (ARQ)   │  - Progressive step persistence      │
│  - Distributed locks  │  - Webhook callbacks                 │
├─────────────────────────────────────────────────────────────┤
│  PostgreSQL        │  Docker/Kubernetes Container Manager   │
│  (User data,       │  (User project environments)           │
│   projects, chat)  │  - Per-project isolation               │
└─────────────────────────────────────────────────────────────┘

Read the full file on GitHub · 900 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. 4d ago First seen · 900 lines · 9,646 tokens per session scan A 772352e6be9e

Subscribe to this mod's changes

OpenSail AGENTS.md is an instructions file published in the GitHub repository TesslateAI/OpenSail (637 stars, last pushed 2d ago), licensed Apache-2.0. It adds 9,646 tokens to every session, about $0.0482 per session on Opus 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.