opencolab AGENTS.md

opencolab AGENTS.md is an instructions file for Codex, OpenCode from jimezsa/opencolab. It costs 5,033 tokens per session, scanned A, original, MIT.

A repository guide for OpenColab, a TypeScript and Node.js command-line tool and local gateway for coordinating research projects and AI agents.

In plain words
What is it for?
Use it when modifying OpenColab, following its architecture and naming rules, or running the prescribed development and validation commands.
Why use it?
It tells coding agents which files define the requirements, how the project is organized, and how to build and test it.

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

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 opencolab AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jimezsa/opencolab/agents-md.svg)](https://agentmods.dev/instructions/jimezsa/opencolab/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/jimezsa/opencolab/agents-md"><img src="https://agentmods.dev/badge/instructions/jimezsa/opencolab/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 5,033 This file is loaded in full into every session.
When invoked 5,033 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 $0.05033 $0.05033
Opus 5 $0.02516 $0.02516
Sonnet 5 $0.01007 $0.01007
Haiku 4.5 $0.00503 $0.00503

Measured 3d ago against content hash 63067fe9744c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

opencolab 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 · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Structure & Module Organization

OpenColab is a TypeScript/Node.js ESM CLI and local gateway for a multi-project, multi-agent research workflow. Keep repository guidance aligned with the actual runtime, not aspirational structure.

Top-level sources of truth:

  • docs/spec.md: source of truth for requirements and architecture.
  • docs/VISION.md: product direction and long-term intent.
  • README.md: quickstart, high-level overview, and condensed runtime/reference guide.
  • package.json: npm package metadata, published CLI surface, and pack/publish lifecycle hooks.
  • pnpm-workspace.yaml: root pnpm workspace definition; includes src/web/client/ so one root install provisions the Vite web UI dependencies used by pnpm run build.
  • install.sh: package-first macOS/Linux installer, managed-install manifest writer, and command shim setup, with optional --hacky git-clone fallback.
  • install.ps1: package-first Windows PowerShell installer, managed-install manifest writer, and command shim setup, with optional --hacky git-clone fallback.
  • projects/SKILLS/: shared built-in skill library copied into agent prompts, not per-project duplicates, including search, summarization, grounded paper QA, scientific LaTeX paper/report writing, image, architecture-diagram, and iterative experiment-loop workflows. Packaged installs must ship this directory too.
  • src/: TypeScript implementation.
  • src/web/: OpenColab Studio implementation, with read-only gateway API handlers in server/, shared DTOs in shared/, and the Vite/React/Tailwind/shadcn client workspace in client/.
  • src/agent-templates/: built-in agent markdown scaffolds loaded by the runtime when seeding agent files and prompt context, with shared files in shared/ and role-specific folders such as professor/, beginner/, autoresearch/, and specialist/. Role AGENTS.md templates should stay concise and avoid restating detailed rules already owned by shared files or injected built-in guidance. Packaged installs must ship the runtime-accessible equivalents.
  • tests/: Node node:test suite.

Read the full file on GitHub · 171 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 · 171 lines · 5,033 tokens per session scan A 63067fe9744c

Subscribe to this mod's changes

opencolab AGENTS.md is an instructions file published in the GitHub repository jimezsa/opencolab (11 stars, last pushed 20d ago), licensed MIT. It adds 5,033 tokens to every session, about $0.0252 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.