agentmods.dev

opengeni AGENTS.md

A guide for working in OpenGeni, a TypeScript and Bun software stack with an API, web app, background worker, database, and messaging services.

In plain words
What is it for?
Use it when navigating the repository, starting its local services, changing session or event flows, updating architecture documentation, or preparing pull requests.
Why use it?
It gives agents a map of the system and explains which documentation and commands to use before changing its architecture or running the full local stack.

Instructions file for CodexOpenCode

115 yesterday A scan 21,782 tokens original Apache-2.0
View the source file Cloudgeni-ai/opengeni
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/cloudgeni-ai/opengeni/agents-md
Clone the repo
git clone --depth 1 https://github.com/Cloudgeni-ai/opengeni

Made for: Codex, OpenCode.

Per session 21,782 This file is loaded in full into every session.
When invoked 21,782 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 $0.21782 $0.21782
Opus 5 $0.10891 $0.10891
Sonnet 5 $0.04356 $0.04356
Haiku 4.5 $0.02178 $0.02178

Measured yesterday against content hash 8096d7ea3c34, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

opengeni 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 yesterday.

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.

The Docker sandbox image includes Terraform, Checkov, AnyDoc, Azure CLI, GitHub CLI, git, jq, curl, and base shell utilities. AnyDoc is a pinned local document-to-Markdown parser; its matching `document-parsing` guidance
AGENTS.md · 365 lines

How it starts

The opening of the file, as written. The whole thing — 365 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent / automation notes (OpenGeni)

This repository is a clean TypeScript/Bun stack. The public API is session-based.

Start here for orientation: docs/architecture.md. It is the canonical whole-system map — what OpenGeni is, the load-bearing invariants, the current workspace layout, the major ownership boundaries, and the "if you're changing X, read Y first" routing index. Read it before navigating an unfamiliar area, and keep it current: if your change adds/removes/renames an app, package, example workspace, or sandbox backend; alters an architectural invariant, the data-flow, or the session/turn lifecycle; or changes which file is canonical for a change area — update docs/architecture.md in the same change. A stale map is a bug. (This file, AGENTS.md, owns how to run and operate the stack; architecture.md owns how the system is shaped.)

When the user says "start the dev server", "spin it up", or "run the full stack", they mean the steps under Full local stack.

Full Local Stack

The stack means everything needed to run the Hono API, React web app, Temporal worker, Postgres event store, Core NATS realtime bus, Temporal service, and configured OpenAI Agents SDK sandbox backend.

  1. Start the full local stack:

    bun run dev

    This installs dependencies, starts the Docker infrastructure, runs migrations, builds the local sandbox image, and starts API, worker, and web processes.

Manual equivalent:

  1. Install dependencies:

    bun install

  2. Start infrastructure:

    docker compose up -d postgres nats temporal garage garage-init
bun run db:migrate
bun run db:provision-roles

  3. Build the local sandbox image when using Docker sandbox:

    docker build -f docker/sandbox.Dockerfile -t opengeni-sandbox:local .

  4. Copy .env.example to .env and configure at least:

    • OPENGENI_DATABASE_URL
    • OPENGENI_NATS_URL
    • OPENGENI_TEMPORAL_HOST
    • OPENGENI_STARTUP_DEPENDENCY_RETRY_* when dependencies need longer startup windows
    • OpenAI or Azure OpenAI credentials
    • OPENGENI_SANDBOX_BACKEND (see Sandbox Notes for the full backend list; docker is the default for local dev)
    • sandbox preparation profiles / env allowlist when needed

Read the full file on GitHub · 365 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. yesterday First seen · 365 lines · 21,782 tokens per session scan A 8096d7ea3c34

Subscribe to this mod's changes

opengeni AGENTS.md is an instructions file published in the GitHub repository Cloudgeni-ai/opengeni (115 stars, last pushed yesterday), licensed Apache-2.0. It adds 21,782 tokens to every session, about $0.1089 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.

Backend and APIsDatabasesWriting and docsagentsbuninfrastructureopenaitemporaltypescript
Related

Other instructions, from other repositories

agent-intel-mcp AGENTS.md

AGENTS.md instructions for danieloza/agent-intel-mcp, covering agents.md, mission, stack, working rules and validation.

danieloza/agent-intel-mcp · 281 tokens

E2B CLAUDE.md

Instructions for e2b-dev/E2B: Use pnpm for node and uv for python to install and update dependencies. Run pnpm run format, pnpm run lint and pnpm run typecheck before committing changes. When modifying the SDK packages, ensure equivalent changes are applied to both JS as well as sync and async Python implementations.…

e2b-dev/E2B · 306 tokens

ax AGENTS.md

Instructions for ax-llm/ax, covering ax repository guide, what this file is for, repository layout, canonical docs and current project defaults.

ax-llm/ax · 1,548 tokens

langgraphjs AGENTS.md

Instructions for langchain-ai/langgraphjs, covering repository instructions and corridor security analysis.

langchain-ai/langgraphjs · 54 tokens

studio AGENTS.md

AGENTS.md instructions for decocms/studio, covering repository guidelines, documentation philosophy, commands, development and start full dev environment (migrations + client + server).

decocms/studio · 8,900 tokens

AI-Gateway AGENTS.md

Instructions for Azure-Samples/AI-Gateway, covering agents.md, directory structure, labs/, modules/ and shared/.

Azure-Samples/AI-Gateway · 1,322 tokens