agentmods.dev

claudius AGENTS.md

A set of coding instructions for ADE, a desktop app development environment built around a Tauri desktop shell, a SolidJS interface, and an agent server.

In plain words
What is it for?
It helps with work on the desktop shell, frontend, agent server, shared UI, API client, and supporting utilities.
Why use it?
It gives an agent the project’s architecture and package roles, reducing the chance of changes being made in the wrong part of the application.

Instructions file for CodexOpenCode

91 6mo ago A scan 2,209 tokens original Apache-2.0
View the source file crisogray/claudius
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/crisogray/claudius/agents-md
Clone the repo
git clone --depth 1 https://github.com/crisogray/claudius

Made for: Codex, OpenCode.

Per session 2,209 This file is loaded in full into every session.
When invoked 2,209 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 $0.02209 $0.02209
Opus 5 $0.01104 $0.01104
Sonnet 5 $0.00442 $0.00442
Haiku 4.5 $0.00221 $0.00221

Measured 3d ago against content hash ecb9de15990e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claudius 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 3d 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 · 284 lines

How it starts

The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ADE: Agent Development Environment

Fork of OpenCode focused on desktop app development.

Architecture

Package Structure

packages/
  desktop/     # Tauri v2 shell, sidecar management
  app/         # SolidJS frontend, context providers, pages
  opencode/    # Agent server, tools, snapshots (runs as sidecar)
  ui/          # Shared components, themes, @pierre/diffs integration
  sdk/         # Auto-generated API client, SSE events
  util/        # Helpers (encoding, binary search, retry)

Desktop App (packages/desktop)

Tauri v2 app that wraps the frontend and manages the opencode CLI as a sidecar:

  • src-tauri/src/lib.rs - Main app logic, sidecar spawning, window creation
  • src-tauri/src/cli.rs - CLI installation/sync to ~/.opencode/bin/opencode
  • src/index.tsx - Entry point, renders app inside ServerGate

Sidecar flow:

Tauri app starts
  -> spawn_sidecar("opencode serve --port={port}")
  -> inject port via window.__OPENCODE__
  -> frontend connects via HTTP/SSE to localhost:{port}

Tauri commands: kill_sidecar, install_cli, ensure_server_started

App Package (packages/app)

SolidJS frontend with nested context providers:

PlatformProvider (web vs desktop abstraction)
  ServerProvider (connection management)
    GlobalSDKProvider (SDK client + global events)
      GlobalSyncProvider (projects, providers state)
        Router
          Layout (sidebar, navigation)
            DirectoryLayout (per-directory scope)
              SDKProvider, SyncProvider (directory-scoped)
                LocalProvider (model, agent, files)
                  TerminalProvider, FileProvider, PromptProvider
                    Session page

Key files:

  • src/pages/layout.tsx - Sidebar with projects/sessions, drag-drop reordering
  • src/pages/session.tsx - Main work surface: messages, prompt input, review tabs
  • src/context/sync.tsx - State management, SSE event handling

Read the full file on GitHub · 284 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. 3d ago First seen · 284 lines · 2,209 tokens per session scan A ecb9de15990e

Subscribe to this mod's changes

claudius AGENTS.md is an instructions file published in the GitHub repository crisogray/claudius (91 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 2,209 tokens to every session, about $0.0110 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.

claudeclaude-codeopencode
Related

Other instructions, from other repositories

plannotator AGENTS.md

AGENTS.md instructions for backnotprop/plannotator, covering plannotator, project structure, server runtimes, installation and environment variables.

backnotprop/plannotator · 33,144 tokens

golembot CLAUDE.md

Instructions for 0xranx/golembot, covering golembot — project conventions for claude code, architecture hard constraints, things you must never do, interface change rules and file responsibility boundaries.

0xranx/golembot · 1,141 tokens

solo AGENTS.md

Instructions for solo-agent/solo, covering project testing rules and project service lifecycle rules.

solo-agent/solo · 306 tokens

OpenCode-GraphAgent CLAUDE.md

Instructions for LeXwDeX/OpenCode-GraphAgent, covering claude.md, what this is, commands, quality gates and build & codegen.

LeXwDeX/OpenCode-GraphAgent · 4,083 tokens

superset CLAUDE.md

Claude Code instructions for superset-sh/superset, a project described as: Superset is an agentic IDE to orchestrate 100+ coding agents in parallel. Run any agent with your own subscription.

superset-sh/superset · 4 tokens

awesome-copilot-id AGENTS.md

Instructions for GulajavaMinistudio/awesome-copilot-id, covering communication, explanation and documentation, markdown formatting, user communication style and workflow & methodology.

GulajavaMinistudio/awesome-copilot-id · 7,686 tokens