See what an AI agent's command would destroy before it runs
A gate in the hook path of Claude Code, Codex, Cursor and Copilot. It shows what a command would delete, backs it up first, and asks or refuses by your policy. Start in observe mode: nothing blocked, a report of what it would have caught. Open source, Rust.
Hi Product Hunt, I'm Manoj. I build Termaxa because coding agents now run shell commands on their own, and the failures that make the news happen inside the permissions people already gave them: a cleanup that takes the wrong directory, a force push, a reset.
Termaxa sits in the agent's hook path. For each command it works out what would be touched (how many files a delete takes, whether a push removes commits, which uncommitted edits a reset would discard), copies what it can before anything runs, then allows, asks or refuses by a policy you can read. Every decision goes into a record the agent can't rewrite.
Earlier this week I measured 36 models on ten ordinary repo requests, each answer judged by the gate and then run on a throwaway repo. Asked to "undo my last commit", 19 of them ran git reset --hard and destroyed uncommitted work nobody had mentioned. The gate only asked about that command, so this week's 0.21.0 fixes it: it previews what the reset would discard and snapshots it first. The write-up is on DEV: https://dev.to/zerodrop/asked-to...
If you'd rather start without changing anything, observe mode (termaxa init --observe) runs every command as before and termaxa report shows what enforcement would have asked, denied, and let run with no copy. A short floor of catastrophic commands stays enforced either way.
It's free and open source (MIT/Apache-2.0), a single Rust binary, and works with Claude Code, Codex, Cursor and Copilot CLI. I publish every bypass found against it: five advisories so far, one reported by an outside researcher, and a list of every bug found in real use. You can try to beat it without installing anything at play.termaxa.com.
What I'd value most: if your team runs agents unattended, run termaxa replay on your agents' transcripts (it executes nothing) and tell me what it shows, or what got in the way.
About Termaxa on Product Hunt
“See what an AI agent's command would destroy before it runs”
Termaxa launched on Product Hunt on October 8th, 2026 and earned 73 upvotes and 10 comments, placing #26 on the daily leaderboard. A gate in the hook path of Claude Code, Codex, Cursor and Copilot. It shows what a command would delete, backs it up first, and asks or refuses by your policy. Start in observe mode: nothing blocked, a report of what it would have caught. Open source, Rust.
On the analytics side, Termaxa competes within Open Source, Developer Tools, GitHub and Security — topics that collectively have 634.9k followers on Product Hunt. The dashboard above tracks how Termaxa performed against the three products that launched closest to it on the same day.
Who hunted Termaxa?
Termaxa was hunted by Manoj Pandhare. 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 Termaxa including community comment highlights and product details, visit the product overview.
Manoj Pandhare
Hi Product Hunt, I'm Manoj. I build Termaxa because coding agents now run shell commands on their own, and the failures that make the news happen inside the permissions people already gave them: a cleanup that takes the wrong directory, a force push, a reset.
Termaxa sits in the agent's hook path. For each command it works out what would be touched (how many files a delete takes, whether a push removes commits, which uncommitted edits a reset would discard), copies what it can before anything runs, then allows, asks or refuses by a policy you can read. Every decision goes into a record the agent can't rewrite.
Earlier this week I measured 36 models on ten ordinary repo requests, each answer judged by the gate and then run on a throwaway repo. Asked to "undo my last commit", 19 of them ran git reset --hard and destroyed uncommitted work nobody had mentioned. The gate only asked about that command, so this week's 0.21.0 fixes it: it previews what the reset would discard and snapshots it first. The write-up is on DEV: https://dev.to/zerodrop/asked-to...
If you'd rather start without changing anything, observe mode (termaxa init --observe) runs every command as before and termaxa report shows what enforcement would have asked, denied, and let run with no copy. A short floor of catastrophic commands stays enforced either way.
It's free and open source (MIT/Apache-2.0), a single Rust binary, and works with Claude Code, Codex, Cursor and Copilot CLI. I publish every bypass found against it: five advisories so far, one reported by an outside researcher, and a list of every bug found in real use. You can try to beat it without installing anything at play.termaxa.com.
What I'd value most: if your team runs agents unattended, run termaxa replay on your agents' transcripts (it executes nothing) and tell me what it shows, or what got in the way.