agentmods.dev

kosmokrator: Instructions file for Codex

AGENTS.md

kosmokrator AGENTS.md is an instructions file for Codex, OpenCode from OpenCompanyApp/kosmokrator. It costs 3,447 tokens per session, scanned A, original, MIT.

Repository-specific instructions for KosmoKrator, a terminal AI coding agent with text and terminal-style interfaces.

In plain words
What is it for?
Use them when developing or reviewing KosmoKrator, including its agent loop, tools, memory, sessions, and user-interface renderers.
Why use it?
They explain the project's architecture, startup commands, and important directories so changes fit the existing design.

Instructions file for CodexOpenCode

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

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

not rated 20repo 4d ago A scan 3,447 tokens original MIT
View source ↗ OpenCompanyApp/kosmokrator
Reuse

Borrowing it

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

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 kosmokrator AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/opencompanyapp/kosmokrator/agents-md"><img src="https://agentmods.dev/badge/instructions/opencompanyapp/kosmokrator/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,447 This file is loaded in full into every session.
When invoked 3,447 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 $0.03447 $0.03447
Opus 5.5 $0.01379 $0.01379
Sonnet 5.5 $0.00689 $0.00689
Haiku 4.5 $0.00345 $0.00345

Measured 2mo ago against content hash 31ecfdbfc0fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

kosmokrator 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 · 299 lines

How it starts

The opening of the file, as written. The whole thing — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.

KosmoKrator

AI coding agent for the terminal. Mythology-themed CLI built with PHP 8.4, Symfony Console, and a dual renderer (TUI/ANSI).

Quick Start

bin/kosmo              # Run with auto-detected renderer (TUI if available, ANSI fallback)
bin/kosmo --renderer=ansi   # Force ANSI mode
bin/kosmo --no-animation    # Skip the animated intro

Architecture

bin/kosmo → Kernel → AgentCommand → AgentSessionBuilder → AgentLoop (REPL)
                                            ├── ToolExecutor → tools + PermissionEvaluator
                                            ├── ContextManager → compaction, pruning, system prompt
                                            ├── StuckDetector → headless loop convergence
                                            ├── LLM client (AsyncLlmClient + RetryableLlmClient)
                                            ├── UIManager → TuiRenderer | AnsiRenderer
                                            ├── ToolRegistry → coding, shell, task, memory, session, Lua, and subagent tools
                                            └── SubagentOrchestrator → parallel child agents

Key directories

  • src/Agent/ — Agent core: AgentLoop (REPL orchestrator), ToolExecutor, ContextManager, StuckDetector, subagent system
  • src/LLM/ — Native LLM stack: AsyncLlmClient (Amp HTTP, streaming), RetryableLlmClient (decorator), provider registry, model catalog, Codex OAuth, prompt caching, and provider-specific request/response mappers.
  • src/UI/ — Rendering layer with split interface hierarchy
    • UI/Tui/ — Symfony TUI renderer: TuiRenderer, TuiModalManager (dialogs), TuiAnimationManager (breathing/spinners), SubagentDisplayManager, widgets
    • UI/Ansi/ — Pure ANSI fallback: AnsiRenderer, MarkdownToAnsi (with Handler/ for table/list extraction), AnsiTableRenderer
    • UI/Diff/ — Unified diff rendering with word-level highlighting
    • UI/Theme.php — Shared color palette, tool icons, context bar
    • UI/AgentDisplayFormatter.php — Shared agent display utilities (used by both renderers)
    • UI/AgentTreeBuilder.php — Builds agent tree from orchestrator stats
  • src/Tool/ — Tool implementations in Coding/, permission system in Permission/
  • src/Command/ — AgentCommand (main REPL/headless), SetupCommand, ConfigCommand, AuthCommand, gateway/integration commands, slash commands in Slash/, power commands in Power/
  • src/Sdk/ — Stable embeddable PHP SDK over the headless runtime: AgentBuilder, Agent, events, renderers, and configuration helpers
  • src/Acp/ — Agent Client Protocol stdio server, JSON-RPC transport, ACP renderer, and session/MCP overlay bridge
  • src/Integration/ — OpenCompany integration catalog, runtime, docs, credential resolution, and Lua invocation helpers
  • src/Mcp/ — MCP config compatibility, stdio client, trust/permission checks, headless runtime, and Lua bridge
  • src/Lua/ — Lua sandbox, docs service, and native tool bridge
  • src/Session/ — SQLite persistence: sessions, messages, memories, settings
  • src/Task/ — Task tracking system with tool integrations

Read the full file on GitHub · 299 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 · 299 lines · 3,447 tokens per session scan A 31ecfdbfc0fd

Subscribe to this mod's changes

kosmokrator AGENTS.md is an instructions file published in the GitHub repository OpenCompanyApp/kosmokrator (20 stars, last pushed 4d ago), licensed MIT. It adds 3,447 tokens to every session, about $0.0138 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

kosmokrator AGENTS.md compared with instructions from other repositories

kosmokrator AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
kosmokrator AGENTS.mdOpenCompanyApp/kosmokratorInstructions file204d agoMITA3,447Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, 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