Turn what your team learns into everyone’s agent setup
Open-source tools for teams on Claude Code, Codex, Cursor, and Kiro. Harness Recommendations finds what’s broken in your agents’ rules, skills, hooks, and permissions, and what’s missing based on your team’s sessions. Control Plane ships fixes team-wide.
Keeping your coding agents' setup current is becoming another job for senior engineers.
Every time a new model ships, you tweak your prompts, skills, hooks, and rules. You find a better workflow in Claude Code. You fix a recurring issue in Cursor. You add a security rule after a code review catches something.
But which of those changes still hold up? What's quietly broken? And how do you get the good ones onto every engineer's machine?
Right now, keeping up takes a platform team, or your best senior engineers pulled off the work they were hired for.
So today we're launching Harness Recommendations and Harness Control Plane: two open-source tools that find what your AI coding harness needs and roll it out to your whole team.
Harness Recommendations - Checks the rules, skills, hooks and instructions your agents use, including CLAUDE.md, AGENTS.md and MCP config - Flags what's broken or risky: duplicate rules, rules that match no files, permission settings that skip every prompt - Proposes what's missing: new rules, hooks and agents drawn from your team's coding sessions, review feedback and security incidents - Every recommendation comes with evidence, so you decide what to change. It never edits your files.
No generic best practices. Recommendations grounded in how your team actually builds.
Harness Control Plane - Distributes the changes you approve to people, teams or repos, across Claude Code, Codex, Cursor and Kiro - An agent on each machine installs them and reports back, so you can check who received what - A useful instruction one engineer figures out becomes part of everyone's setup
Discover what makes your setup better. Give it to everyone. Repeat.
Earlier this week we launched Agent Desk and Session Intelligence (https://www.producthunt.com/prod...), which show how your agents are configured and how their sessions go. These build on that, so what you learn keeps your agents working well as the work changes.
Try it: the quick start scans a sample repo with Go and a local Postgres. No model, no account. Proposing what's missing needs your session and review data plus your own model key. Both are self-hosted and MIT-licensed.
How do you keep your team's agent setup current today? Tell us what breaks.
About Tetriz Harness on Product Hunt
“Turn what your team learns into everyone’s agent setup”
Tetriz Harness launched on Product Hunt on October 16th, 2026 and earned 61 upvotes and 2 comments, placing #21 on the daily leaderboard. Open-source tools for teams on Claude Code, Codex, Cursor, and Kiro. Harness Recommendations finds what’s broken in your agents’ rules, skills, hooks, and permissions, and what’s missing based on your team’s sessions. Control Plane ships fixes team-wide.
On the analytics side, Tetriz Harness competes within Open Source, Developer Tools, Artificial Intelligence and GitHub — topics that collectively have 1.1M followers on Product Hunt. The dashboard above tracks how Tetriz Harness performed against the three products that launched closest to it on the same day.
Who hunted Tetriz Harness?
Tetriz Harness was hunted by Prasanna R. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
For a complete overview of Tetriz Harness including community comment highlights and product details, visit the product overview.
Prasanna R
Hey Product Hunter,
Keeping your coding agents' setup current is becoming another job for senior engineers.
Every time a new model ships, you tweak your prompts, skills, hooks, and rules. You find a better workflow in Claude Code. You fix a recurring issue in Cursor. You add a security rule after a code review catches something.
But which of those changes still hold up? What's quietly broken? And how do you get the good ones onto every engineer's machine?
Right now, keeping up takes a platform team, or your best senior engineers pulled off the work they were hired for.
So today we're launching Harness Recommendations and Harness Control Plane: two open-source tools that find what your AI coding harness needs and roll it out to your whole team.
Harness Recommendations
- Checks the rules, skills, hooks and instructions your agents use, including CLAUDE.md, AGENTS.md and MCP config
- Flags what's broken or risky: duplicate rules, rules that match no files, permission settings that skip every prompt
- Proposes what's missing: new rules, hooks and agents drawn from your team's coding sessions, review feedback and security incidents
- Every recommendation comes with evidence, so you decide what to change. It never edits your files.
No generic best practices. Recommendations grounded in how your team actually builds.
Harness Control Plane
- Distributes the changes you approve to people, teams or repos, across Claude Code, Codex, Cursor and Kiro
- An agent on each machine installs them and reports back, so you can check who received what
- A useful instruction one engineer figures out becomes part of everyone's setup
Discover what makes your setup better. Give it to everyone. Repeat.
Earlier this week we launched Agent Desk and Session Intelligence (https://www.producthunt.com/prod...), which show how your agents are configured and how their sessions go. These build on that, so what you learn keeps your agents working well as the work changes.
Try it: the quick start scans a sample repo with Go and a local Postgres. No model, no account. Proposing what's missing needs your session and review data plus your own model key. Both are self-hosted and MIT-licensed.
How do you keep your team's agent setup current today? Tell us what breaks.