sekaisync: Instructions file for Codex

AGENTS.md

sekaisync AGENTS.md is an instructions file for Codex, OpenCode from omoinoki/sekaisync. It costs 2,407 tokens per session, scanned A, original, MIT.

A development guide for the SekaiSync project and its connected workspaces. It explains which repositories handle the backend, desktop clients, user experience, and shared Project Sekai knowledge base.

In plain words
What is it for?
Use it to find the relevant workspace, understand repository responsibilities, and follow the project's shared development workflow.
Why use it?
It reduces confusion when a change spans several code repositories or when product-answer rules are mistaken for development instructions. It provides a common map for working across those projects.

Instructions file for CodexOpenCode

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

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

Reuse

Borrowing it

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

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 sekaisync AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/omoinoki/sekaisync/agents-md"><img src="https://agentmods.dev/badge/instructions/omoinoki/sekaisync/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,407 This file is loaded in full into every session.
When invoked 2,407 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 $0.02407 $0.02407
Opus 5.5 $0.00963 $0.00963
Sonnet 5.5 $0.00481 $0.00481
Haiku 4.5 $0.00241 $0.00241

Measured 14d ago against content hash 1c7be8b160ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sekaisync 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 14d 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 · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Agent Guide

This is the single development guide for the connected SekaiSync workspaces. DSH, WinUI3 and UX root AGENTS.md files are reading pointers to this file, not separate policy copies. The members-only memories-of-melody repository is the shared knowledge base for Project OMNK's Project SEKAI-related projects; it owns the experience-library read/write protocol in its own AGENTS.md.

For agents answering Project Sekai questions through the product, use agents/rules/AGENTS.md; those are product query rules, not the development workflow.

Connected Workspaces

Resolve these five folders from the current project's configured paths before working across repositories. When present, read the ignored local path map at work/agent-context/connected-workspaces.local.json; it records checkout locations, not additional rules. Confirm that its destinations still exist before using it.

Folder Responsibility Guidance
sekaisync-cli Backend and shared development workflow This file
dsh-sekaisync-connect DSH plugin Pointer to this file
sekaisync-winui3 Windows desktop client Pointer to this file
sekaisync-ux Shared UX/design workspace; temporarily non-public until complete Pointer to this file
memories-of-melody Shared knowledge base for Project OMNK's Project SEKAI-related projects; Project OMNK members only Its own AGENTS.md read/write protocol

The plugin and desktop submodules in this checkout are not additional connected repositories. Distinguish their pinned copies from the independent checkouts before editing. The official deepseek-harness upstream is a compatibility reference, not one of these five project folders.

Project Map

  • sekaisync/: Python backend, synchronization, extraction, storage, search and fact packs.
  • sekaisync/cli.py, sekaisync/mcp_server.py, sekaisync/http_server.py: public interfaces consumed by clients.
  • tests/: backend regression tests; .github/workflows/ci.yml: supported CI commands and Python versions.
  • agents/deepseek-harness/: SekaiSync Connect plugin, maintained in a separate Git repository and pinned here as a submodule.
  • frontends/WinUI3/: Windows desktop client, also a separate Git repository and submodule.
  • scripts/: development, evaluation, build and migration helpers.
  • work/: ignored local experiments, logs, screenshots and release evidence. store/ contains local data, not source code.

Read the full file on GitHub · 122 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. 14d ago First seen · 122 lines · 2,407 tokens per session scan A 1c7be8b160ae

Subscribe to this mod's changes

sekaisync AGENTS.md is an instructions file published in the GitHub repository omoinoki/sekaisync (23 stars, last pushed 11d ago), licensed MIT. It adds 2,407 tokens to every session, about $0.0096 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 2026-10-03.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,649 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,257 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,159 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens