# Harness Useful

> Local tools for your coding agent.

A desktop app, skills, shared memory and a usage dashboard for the CLI you already run: Claude Code, Codex, OpenCode, PI or Oh My Pi.

By the numbers: 5 harnesses · 13 tools metered · 1 setup for all · 0 telemetry.

## What is Harness Useful?

Harness Useful is a family of four open-source, local tools for coding-agent harnesses such as Oh My Pi, PI, OpenCode, Claude Code and Codex. Harness Desktop is the window, Harness Skills the workflow, Harness Memory the shared project memory and Harness Dashboard the usage and cost meter. Each works on its own.

## The life of one prompt in the family

Follow a single request through the family: light runs along every connection, and the step happening now lights up.

1. **You type a prompt** (you → Harness Desktop). In the Desktop chat of an open project, with the CLI you already use and your own login. A real window around your harness.
2. **Desktop hands it to your CLI** (Harness Desktop → your CLI). First the hooks you approved add their context: search memory first, check skills and limits, check the branch. One set of rules for every harness.
3. **The agent searches Harness Memory** (your CLI → Harness Memory). note_search and script_list for this git repository, before any work starts. Every session starts informed.
4. **What earlier sessions learned comes back** (Harness Memory → your CLI). Typed notes (decisions, fixes, locations) written by any of your harnesses. Nothing is relearned.
5. **Skills pick a lane and plan** (your CLI → Harness Skills). A read-only scout researches the code, then the planner drafts work packages with acceptance criteria. Understood before it is changed.
6. **You approve the plan** (Harness Desktop → you). Nothing is edited before you say yes, and risky calls ask again while the work runs. You stay in control.
7. **Implement, review, security review** (Harness Skills → your CLI). Workers build in parallel; fresh reviewers check correctness and security, and any finding loops back for repair. The agent does not grade its own work.
8. **Dashboard checks limits and prices the run** (your CLI → Harness Dashboard). Limits and budgets before long work, then every call priced from the session log, subagents included. Know what a feature cost.
9. **The cost shows up in Desktop** (Harness Dashboard → Harness Desktop). Ecosystem shows cost, tokens and cost per prompt next to the family status. The loop closes where it started.

## What changes the day you add the family

| Before | With the family | Tool |
| --- | --- | --- |
| Every session starts cold and rediscovers the repo. | Sessions start with the repo’s notes, recalled by any harness. | Harness Memory |
| The agent jumps straight into edits. | Research, a plan you approve, parallel workers, fresh reviews. | Harness Skills |
| Read the diff in a pager, retype your feedback. | Comment on any diff line and send it all as one prompt. | Harness Desktop |
| Cost shows up as a bill at the end of the month. | Cost per prompt, branch and model, with live plan limits. | Harness Dashboard |
| Five CLIs, five config formats, secrets in plain sight. | One window for config and extensions, secrets masked. | Harness Desktop |

## Which tool do I need?

| Tool | What it does | Runs as | Platforms | Works with | Where data lives | License |
| --- | --- | --- | --- | --- | --- | --- |
| [Harness Desktop](https://harness-useful.com/desktop) | Your coding-agent CLI in a native desktop window: chat, sessions, review comments, config and extensions. | Desktop app | macOS (Apple Silicon and Intel), Linux (AppImage, deb, rpm), Windows (NSIS installer, MSI) | OMP, PI, OpenCode, Claude Code, Codex | Hooks as JSON files in harness-hooks/hooks in your data folder | GPL-3.0-or-later |
| [Harness Skills](https://harness-useful.com/skills) | us-* skills that take a request to reviewed, verified work. | Plugin or skills loaded by your harness | macOS, Linux, Windows (PowerShell installer for OpenCode and Codex) | Oh My Pi, Claude Code, OpenCode, Codex | Plugin files in your harness | GPL-3.0-only |
| [Harness Memory](https://harness-useful.com/memory) | One shared project memory for your coding agents. | Local stdio MCP server (one binary) | macOS (Apple Silicon and Intel), Linux (x86_64), Windows | Any MCP client, including Claude Code, Codex, OMP, PI, OpenCode | memory.sqlite3 in the harness-memory folder of your user data directory | GPL-3.0-or-later |
| [Harness Dashboard](https://harness-useful.com/dashboard) | Token usage and API-equivalent cost across your AI coding tools. | Desktop app with an optional MCP server | macOS, Linux (x86_64), Windows | Claude Code, Codex, Gemini CLI, Copilot CLI, Copilot Chat, OpenCode, pi, omp, Zed, Cline, Roo Code, Kilo Code, Cursor | A local SQLite database on your machine | GPL-3.0-or-later |

## The four tools

### Harness Desktop

Your coding-agent CLI, in a native desktop window. Harness Desktop is a native desktop app for coding-agent harness CLIs that runs on top of the CLI you already have installed.

[Harness Desktop](https://harness-useful.com/desktop) · [Markdown](https://harness-useful.com/desktop.md) · [GitHub](https://github.com/MSpiechowicz/harness-useful-desktop)

### Harness Skills

From a natural-language request to reviewed, verified work. Harness Skills is a set of owned us-* skills for Oh My Pi, Claude Code, OpenCode and Codex that take a natural-language request to reviewed, verified work.

[Harness Skills](https://harness-useful.com/skills) · [Markdown](https://harness-useful.com/skills.md) · [GitHub](https://github.com/MSpiechowicz/harness-useful-skills)

### Harness Memory

Project memory for your AI coding agents, in one local binary. Harness Memory is a local stdio MCP server that gives Claude Code, Codex, OMP, PI, OpenCode and any other MCP client one shared project memory.

[Harness Memory](https://harness-useful.com/memory) · [Markdown](https://harness-useful.com/memory.md) · [GitHub](https://github.com/MSpiechowicz/harness-useful-memory)

### Harness Dashboard

Token usage across your AI coding tools, in one local app. Harness Dashboard is a local desktop app that reads the sessions your AI coding tools already write to disk and shows where your tokens and money go.

[Harness Dashboard](https://harness-useful.com/dashboard) · [Markdown](https://harness-useful.com/dashboard.md) · [GitHub](https://github.com/MSpiechowicz/harness-useful-dashboard)

## One install. It brings the family.

Install Desktop, then Ecosystem → Run recommended setup. It installs Dashboard, Memory and Skills, registers their MCP servers in every harness it finds and adds the family hooks, asking before each step.

### macOS · Linux

```sh
curl -fsSL https://raw.githubusercontent.com/MSpiechowicz/harness-useful-desktop/main/install.sh | sh
```

### Windows

```powershell
powershell -ExecutionPolicy Bypass -c "irm https://raw.githubusercontent.com/MSpiechowicz/harness-useful-desktop/main/install.ps1 | iex"
```

## Frequently asked questions

### What is Harness Useful?

Harness Useful is a family of four open-source, local tools for coding-agent harnesses such as Oh My Pi, PI, OpenCode, Claude Code and Codex. Harness Desktop is the window, Harness Skills the workflow, Harness Memory the shared project memory and Harness Dashboard the usage and cost meter. Each works on its own.

### Which Harness Useful tool should I start with?

Start with Harness Desktop. Install it, then open Ecosystem and choose Run recommended setup. After you confirm each part, it installs Harness Dashboard, Harness Memory and Harness Skills, registers their MCP servers in each detected harness and adds the family hooks. You can also install any tool by itself.

### Do the Harness Useful tools work separately?

Yes. Each tool has its own repository, installer and README, and works without the others. Harness Memory is a standalone MCP server, Harness Dashboard is a standalone app, and Harness Skills installs straight into your harness. They work best together, and Desktop connects them through Recommended setup.

### Which coding agents do the tools support?

Harness Desktop supports Oh My Pi and PI, with partial OpenCode support and chat previews for OpenCode, Claude Code and Codex. Harness Skills supports Oh My Pi, Claude Code, OpenCode and Codex. Harness Memory works with any MCP client. Harness Dashboard reads 13 tools, including Gemini CLI, GitHub Copilot, Zed, Cline, Roo Code, Kilo Code and Cursor.

### Is Harness Useful free and open source?

Yes. All four tools are open source on GitHub under the GNU General Public License version 3. Harness Desktop, Harness Memory and Harness Dashboard are GPL-3.0-or-later, and Harness Skills is GPL-3.0-only. You can read the source, install the tools at no charge and follow each project’s releases on its GitHub repository.

### Do the tools collect telemetry or need an account?

No. Harness Desktop has no telemetry, no accounts and stores no tokens. Harness Dashboard never uploads your usage. Harness Memory opens no network connection unless you set up a team database. The tools make a few optional requests, such as signed update checks against GitHub, which you can turn off.

### Where is my data stored?

On your machine. Harness Memory keeps notes in a SQLite file, memory.sqlite3, in the harness-memory folder of your user data directory. Harness Dashboard keeps usage in a local SQLite database. Harness Desktop keeps hooks as JSON files in harness-hooks/hooks. Harness Skills is plugin files that your harness reads.

### Which operating systems are supported?

Harness Desktop runs on macOS (Apple Silicon and Intel), Linux and Windows. Harness Memory supports macOS, Linux on x86_64 and Windows. Harness Dashboard supports macOS, Linux on x86_64 and Windows. Harness Skills installs into your harness with a short command and needs Node.js 22 or newer.

### How do the tools connect to each other?

Through MCP servers and hooks. Harness Memory and Harness Dashboard are MCP servers that your harness starts. Harness Desktop registers them in each detected harness and adds hooks that ask agents to search memory first, save what they learned and check limits before long work. Harness Skills adds the us-* workflow skills.

### How do I install Harness Useful?

Install Harness Desktop with one command: on macOS and Linux run the curl install script, on Windows run the PowerShell install command. Both verify the release checksum. Then use Ecosystem and Run recommended setup to add the other tools. Each tool also has its own install command on its page.

## Links

- Website: https://harness-useful.com/
- FAQ: https://harness-useful.com/faq