Skip to content
This repository was archived by the owner on Jul 4, 2026. It is now read-only.

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

43 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

📦 Archived!

In December 2025 this was really useful working around some of the limitations of models, and maxing out their inherent capabilities.

Models and harnesses have moved on a lot since and most of these techniques work against what they now do natively.


FeaturesInstallationUser Guide

THE
SCIENTIST

An OpenCode config pack designed for operating long-horizon, multi-task projects.

Models like Opus 4.5 are great for creative work in short back-and-forths; GPT-5.2 excels when left to complete more narrowly-scoped problems. This methodology aims to support the execution of long-running and open-ended projects by using simple mechanisms that resist LLMs' post-training impulses.

Quick Start

$ opencode

█░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░▒
█░                                                                      ░▒  
█░  Help me set up https://github.com/djgrant/the-scientist             ░▒
█░                                                                      ░▒  
█░  Build   Claude Opus 4.5 (latest) Anthropic                          ░▒
█░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░▒

Features

A baseline set of features are included. These can be used alongside any project and global configs you have already defined. See merging configs and installation.

Primary Agents

Agents that you interact with directly.

Agent Description
delegate Orchestrates long-horizon projects via work packages and subagents
distill Distills analysis by interviewing the user to extract core insights

Sub-Agents

Agents that receive delegated tasks.

Sub-Agent Description
architect Attempts to keep project entropy low
critique Generates insights through adversarial dialectic
diverge Looks for edge-of-distribution alternatives
qa Performs end-to-end testing to validate/invalidate hypotheses
ux Explores solution with a human-centric perspective

Commands

Slash commands for common workflows.

Command Description
/browser-test Test web UI in browser with screenshots
/files-to-prompt Generate a prompt from repo files for use with other AI tools
/init-scientist Initialise project with the-scientist directory structure
/update-scientist Update the-scientist to the latest version

Skills

Lazily-loaded instructions that guide agent behavior.

Skill Description
browser Take screenshots and interact with web UIs via Playwright
divergent-thinking Use verbalised sampling to mitigate mode collapse
orchestrate Core methodology for orchestration using sub-agents and work packages
orchestrate-map-reduce Fan out to multiple agents, validate solutions, find a winner
orchestrate-project Define, execute, review, test, and iterate on sub-tasks
read-learnings Review previously recorded project learnings
record-learnings Record notable discoveries for future reference
scientific-method Hypothesis-driven iteration
simplify Find the essence of a solution via iterative simplification
work-packages Structured approach for multi-agent task handoff

Tools

Custom tools available to agents.

Tool Description
files-to-prompt Generate prompts from repo files using files-to-prompt

Installation

First, install the config pack globally, then initialise it for each project you want to use it in.

Global Setup

Option 1: As an overlay config

git clone https://github.com/djgrant/the-scientist.git

# Add to your shell profile (.zshrc, .bashrc, etc.)
export OPENCODE_CONFIG_DIR={path_to_cloned_repo}

Loads after your global and project settings. See custom directory docs.

Options 2: As your global config

git clone https://github.com/djgrant/the-scientist.git ~/.config/opencode

Loads before your project settings. You can alternatively symlink to this location.

Project Setup

Run /init-scientist within your repo. This will set up:

  • .opencode/work/ for work packages
  • .opencode/learnings/ for project learnings
  • Optionally, an AGENTS.md template

For tools that require Python dependencies (browser, files-to-prompt), run /init-agentkit from your global agentkit config.

Updating

To update the-scientist to the latest version, you have two options:

1/ Run update command

/update-scientist

The command will instruct the agent to merge any local changes and check for new prerequisites.

2/ Pull Manually

cd {path-to-the-scientist}
git pull

User Guide

The most important agent in this setup is you.

A clear, well-thought-out vision is to an LLM what a good data structure is to code.

Approach

Here are a couple of suggestions you can try as a starting point.

Existing Projects

Prompt the delegate agent to:

Commission thorough research looking for gaps and opportunities in this project. 
Explore a broad range of areas and ideas. 

The delegate agent, using a selection of skills and agents, will ultimately produce an undoubtedly large set of recommendations.

To find the gems in the ruff, switch to the distill agent, and let it prompt you to find out what's worth pursuing.

You can then switch back to the delegate agent and ask it to undertake the work.

New Projects/Features

For new projects, you can switch the flow around:

  1. Start opencode in plan mode and explain your vision to the agent
  2. Leave some questions open (exploration can be delegated to subagents)
  3. Once the vision is well-formed ask the plan agent to create a "scoping work package" to capture the vision and areas to explore
  4. Compact the conversation (/compact)
  5. Switch to delegate mode (tab key), then ask the agent to "read the work package and execute the vision"

The delegate agent will then use subagents to create more detailed work packages, which, in turn, get delegated to other subagents to implement.

Use Cases

I have so far found this setup valuable for:

  1. Deep-dives e.g find performance/security/ux gaps and opportunities
  2. Feasibility experiments e.g. build out features to generate insights
  3. Personal applications e.g. holiday planner, home automation etc.

This system may also be valuable to developers who gain less enjoyment from manually hand-holding agents. Once a long-running project gets started, you get a reasonably long interval to divert your attention toward more focussed tasks.

Whether you decide to ship the code this system produces, or use it as the inspiration for a more-considered build, will depend entirely on your context and risk tolerance.

Operating Costs

When you use the delegate agent, orchestrated tasks can run for anything up to an hour (even with agents working in parallel).

It is therefore recommended to be on subscription pricing e.g. Claude Code, Github Copilot etc. (set up via opencode auth login). In my experience, API pricing can end up being a factor of 100x more expensive.

Recommended Models

I am personally using this with Opus 4.5. No doubt, Gemini 3, GPT 5.2 and other SOTA-class models will work similarly well. Mixing models will probably boost performance.

I strongly suspect that the system will break down with a model like Sonnet 4.5, and will be no more cost effective.

Note: You can set a default model in your global or project opencode configuration.

Additional Setup

It is recommended to add a vision statement to your project's AGENTS.md (agents are instructed to align to this), along with any definitions of what good looks like to you.


License

MIT License - Copyright (c) 2026 Daniel Grant

About

An OpenCode config pack designed for operating long-horizon, multi-task projects

Resources

Stars

8 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages