Oxide-Agent AGENTS.md

Project instructions for Oxide-Agent, a Telegram bot that supports text, voice, images, documents, memory, sandbox tasks, and a web console.

In plain words
What is it for?
Use it when working on the Oxide-Agent Rust service, Telegram integrations, storage, web console, model providers, or manager control plane.
Why use it?
It explains the project’s architecture, technology stack, scale limits, and design rules so coding agents can make changes that fit the existing system.

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/0fl01/oxide-agent/agents-md
Clone the repo
git clone --depth 1 https://github.com/0FL01/Oxide-Agent

Made for: Codex, OpenCode.

Per session 3,928 This file is loaded in full into every session.
When invoked 3,928 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 $0.03928 $0.03928
Opus 5 $0.01964 $0.01964
Sonnet 5 $0.00786 $0.00786
Haiku 4.5 $0.00393 $0.00393

Measured 2d ago against content hash 05033888aab2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Oxide-Agent 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 2d 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 · 197 lines

How it starts

The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Oxide Agent

Oxide Agent is a Telegram bot with Agent Mode on top of multiple LLM providers. It handles text, voice, images, documents, topic-scoped memory, sandbox tasks, a web console (Life Mode), and a manager control plane.

Stack: Rust 2024 edition, teloxide, SQLx/Postgres durable storage, Leptos, native integrations with OpenRouter, Anthropic Messages (generic, covers MiniMax), OpenAI-Base (covers ZAI/Mistral/custom), ChatGPT/Codex OAuth, and OpenCode Go/Zen. Gemini-family models are accessed through OpenRouter routes, not a direct Google Gemini provider.

Branch

Default branch: main.

Scale and decision principles

  • Personal use, up to 2-3 people; target load up to 5 RPS.
  • No sharding, HA, extra queues, multi-layer abstractions, or heavy observability without proven need.
  • Optimize only after a real bottleneck; if a fix leaves a class of problems open, redesign the root cause rather than preserve a broken architecture.

Implementation bias

  • Smallest fundamentally correct change; preserve architecture only when it is sound.
  • Boring, explicit, locally understandable code over generic frameworks.
  • No new crates, services, queues, caches, storage backends, protocols, or abstraction layers unless clearly required.
  • Add abstraction only after real duplication or multiple call sites exist.
  • Document known limitations instead of building generalized designs for hypothetical needs.

Workspace Overview

Main crates

  • oxide-agent-core - agent domain: execution, hooks, compaction, storage facade, LLM providers, sandbox, reminder/SSH/manager providers.
  • oxide-agent-runtime - session runtime orchestration and transport-agnostic progress.
  • oxide-agent-transport-telegram - Telegram transport: handlers, routing, views, progress, topic/thread integration.
  • oxide-agent-transport-web - Web console backend and E2E test transport: HTTP API (axum), scripted LLM, SSE streaming, Life Mode executor/routes.
  • oxide-agent-web-contracts - Shared web API types: auth, config, events, sessions, tasks, life.
  • oxide-agent-web-ui - Leptos web console frontend: components, SSE streaming, markdown rendering, dark theme, Life Mode UI.
  • oxide-agent-sandboxd - Docker sandbox broker daemon; Unix socket, Docker access.
  • oxide-agent-telegram-bot - Telegram bot binary.
  • oxide-browser-contracts - Shared REST contract types between the native browser sidecar and the core browser-live client; independent of core/runtime internals.
  • oxide-browser-sidecar - Native Rust Chromium sidecar binary; talks CDP directly, serves the browser-live REST API (sessions, actions, snapshots, screenshots).

Read the full file on GitHub · 197 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. 2d ago First seen · 197 lines · 3,928 tokens per session scan A 05033888aab2

Subscribe to this mod's changes

Oxide-Agent AGENTS.md is an instructions file published in the GitHub repository 0FL01/Oxide-Agent (86 stars, last pushed 28d ago), licensed MIT. It adds 3,928 tokens to every session, about $0.0196 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.

Related

Other instructions, from other repositories

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

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 · 6,785 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 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 · 4,345 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js 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 · 7,296 tokens