What is Opencode-Assistant AGENTS.md?

Project instructions for developing Opencode-Assistant, a Telegram bot that lets users run, monitor, schedule, and remember coding tasks through Telegram.

Understanding the codebase and working consistently with its TypeScript, Node.js, Telegram, OpenCode, and test conventions.

They give coding agents the project's purpose, tools, structure, and testing setup in one place.

How JohanYP/Opencode-Assistant configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to JohanYP/Opencode-Assistant. 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/JohanYP/Opencode-Assistant/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/JohanYP/Opencode-Assistant

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/johanyp/opencode-assistant/agents-md/github.svg)](https://agentmods.dev/instructions/johanyp/opencode-assistant/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/johanyp/opencode-assistant/agents-md"><img src="https://agentmods.dev/badge/instructions/johanyp/opencode-assistant/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/johanyp/opencode-assistant/agents-md"><img src="https://agentmods.dev/badge/instructions/johanyp/opencode-assistant/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,972 This file is loaded in full into every session.

When invoked 1,972 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.

Model	Per session	Once invoked
Fable 5.1	$0.01972	$0.01972
Opus 5.5	$0.00789	$0.00789
Sonnet 5.5	$0.00394	$0.00394
Haiku 4.5	$0.00197	$0.00197

Measured 2mo ago against content hash 58d9822d8cd3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Opencode-Assistant 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 · 272 lines

How it starts

The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Instructions for AI agents working on this project.

About the project

Opencode-Assistant is a Telegram-based personal AI assistant powered by OpenCode. It lets a user run, monitor and schedule coding tasks (with continue/cancel deliveries), manage MCP servers, and keep persistent memory across sessions — all through Telegram.

Functional requirements, features, and development status are in PRODUCT.md.

Technology stack

Language: TypeScript 5.x
Runtime: Node.js 20+
Package manager: npm
Configuration: environment variables (.env)
Logging: custom logger with levels (debug, info, warn, error)

Core dependencies

grammy - Telegram Bot API framework (https://grammy.dev/)
@grammyjs/menu - inline keyboards and menus
@opencode-ai/sdk - official OpenCode Server SDK
dotenv - environment variable loading

Test dependencies

Vitest
Mocks/stubs via vi.mock()

Code quality

ESLint + Prettier
TypeScript strict mode

Architecture

Main components

Bot Layer - grammY setup, middleware, commands, callback handlers
OpenCode Client Layer - SDK wrapper and SSE event subscription
State Managers - session/project/settings/question/permission/model/agent/variant/keyboard/pinned
Summary Pipeline - event aggregation and Telegram-friendly formatting
Process Manager - local OpenCode server process start, stop, and status
Runtime/CLI Layer - runtime mode, config bootstrap, CLI commands
I18n Layer - localized bot and CLI strings to multiple languages

Data flow

Telegram User
  -> Telegram Bot (grammY)
  -> Managers + OpenCodeClient
  -> OpenCode Server

OpenCode Server
  -> SSE Events
  -> Event Listener
  -> Summary Aggregator / Tool Managers
  -> Telegram Bot
  -> Telegram User

State management

Persistent state is stored in settings.json.
Active runtime state is kept in dedicated in-memory managers.
Session/project/model/agent context is synchronized through OpenCode API calls.
The app is currently single-user by design.

Read the full file on GitHub · 272 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.

2mo ago First seen · 272 lines · 1,972 tokens per session scan A 58d9822d8cd3

Subscribe to this mod's changes

Opencode-Assistant AGENTS.md is an instructions file published in the GitHub repository JohanYP/Opencode-Assistant (6 stars, last pushed 5mo ago), licensed MIT. It adds 1,972 tokens to every session, about $0.0079 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 2026-08-31.

ai-assistant claude claude-skills claude-sonnet embeddings mcp

Opencode-Assistant AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Opencode-Assistant AGENTS.mdJohanYP/Opencode-Assistant	Instructions file	6	5mo ago	MIT	A	1,972	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

Opencode-Assistant: Instructions file for Codex