jarvis AGENTS.md

jarvis AGENTS.md is an instructions file for Codex, OpenCode from omnigentx/jarvis. It costs 8,157 tokens per session, scanned A, original, MIT.

A set of repository instructions for Jarvis, an open-source AI assistant in a monorepo, which is one repository containing several related parts. It defines its real-time event system, code organization, and development rules.

In plain words
What is it for?
Working on the Python backend, real-time status updates, server-sent events, WebSocket connections, authentication failures, reconnection behavior, tests, and service structure.
Why use it?
It gives agents shared expectations for reliable streaming, error handling, and modular code. It also requires clarification when a request is unclear.

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/omnigentx/jarvis/agents-md
Clone the repo
git clone --depth 1 https://github.com/omnigentx/jarvis

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 jarvis AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/omnigentx/jarvis/agents-md.svg)](https://agentmods.dev/instructions/omnigentx/jarvis/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/omnigentx/jarvis/agents-md"><img src="https://agentmods.dev/badge/instructions/omnigentx/jarvis/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 8,157 This file is loaded in full into every session.
When invoked 8,157 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.08157 $0.08157
Opus 5 $0.04078 $0.04078
Sonnet 5 $0.01631 $0.01631
Haiku 4.5 $0.00816 $0.00816

Measured 4d ago against content hash 58f09af31fe6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

jarvis AGENTS.md scanned grade A with 1 finding 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 4d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **Dynamic** (runtime, no restart): create the row via `POST /api/agents` (dashboard or curl) or call the `spawn_agent` MCP tool from within Jarvis. The definition lands in the SQLite `agent_definitions` table; `service
AGENTS.md · 561 lines

How it starts

The opening of the file, as written. The whole thing — 561 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Jarvis AI Assistant — Repository Guidelines

  • Repo: Open-source monorepo (omnigentx/jarvis)
  • Core runtime: fast-agent (Python, git submodule at backend/fast-agent)
  • Always reference files repo-root relative (e.g. backend/routes/chat.py:187); never absolute paths.

Core Principles

  1. Realtime monitoring — SSE, WebSocket, or equivalent push protocol. Absolutely no polling. All agent status, tool execution progress, and activity events must stream to clients in real-time via services/activity_stream.py (ActivityStreamManager) and services/sse_progress.py (ProgressManager).

  2. Production-ready code — Every feature must handle edge cases: connection drops, auth failures, SSE reconnection with exponential backoff, timeout handling, graceful degradation. No TODO placeholders or "happy path only" implementations.

  3. Clarification before implementation — When requirements are ambiguous, always present specific questions with options to the user before writing code. Prefer numbered questions that are actionable.

  4. Clean architecture — Code must be modular, well-separated, and easy to extend:

    • Keep files under ~500 LOC; split when exceeding.
    • Extract reusable composables/services; avoid copy-paste.
    • Use clear naming that reflects domain concepts (not generic names).
    • Every component should have a single responsibility.
  5. fast-agent best practices — This project is built on fast-agent. Always:

    • Reference official docs before implementing agent features: Tool Runner, Prompting, Instructions
    • Use ToolRunnerHooks for monitoring and progress tracking (see services/spawn_progress_bridge.py for the pattern).
    • Persist runtime-created agents through services/agent_definitions.py (SQLite). Replaces the legacy file-based agent cards.
    • Understand the session/history model via services/session_service.py.
    • Never bypass fast-agent's built-in capabilities; extend through hooks, not monkey-patching.

Read the full file on GitHub · 561 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. 4d ago First seen · 561 lines · 8,157 tokens per session scan A 58f09af31fe6

Subscribe to this mod's changes

jarvis AGENTS.md is an instructions file published in the GitHub repository omnigentx/jarvis (36 stars, last pushed 7d ago), licensed MIT. It adds 8,157 tokens to every session, about $0.0408 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

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

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

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