cd /news/ai-safety/agentguard-update-open-core-break-gl… · home topics ai-safety article
[ARTICLE · art-125044] src=dev.to ↗ pub= topic=ai-safety verified=true sentiment=· neutral

AgentGuard Update: Open Core, Break-Glass Governance — and the First Real-World Finds

AgentGuard, an open-source security tool for coding agents, has been split into an MIT-licensed engine and a commercial Pro tier, with the CI gate remaining free for public repositories. Version 0.2.2 introduces break-glass governance with time-limited waivers, demonstrated by a test waiver that expires automatically in September 2026. The project has expanded to 85 deterministic tests and reports two real-world finds of invisible characters that differ between model and human views, responsibly disclosed without public naming.

by read2 min views5 publishedSep 9, 2026

When I posted the launch here on dev.to, the pitch was simple: I attacked my own repo — and my own PR bot blocked the attack before merge. A lot has moved since then. Here's the honest update, including the uncomfortable parts.

AgentGuard has been two clearly separated parts since this week:

Why the split? Because a CI gate for coding agents is either a hobby or a product. I chose the latter. The community loses nothing: the engine stays MIT, the Action stays free for public repos. The line is documented in LICENSING.md — in plain text, not fine print.

Every honest security policy needs exceptions. The naive version is the permanent bypass: switch it off once, it stays off forever. Our answer in v0.2.2:

And here's the part that matters to me: we don't claim the expiry works — we demonstrate it publicly. A test waiver (#13) runs in our own repo and expires automatically on 16 Sep 2026. The guardian run after that documents it publicly: commented, warned, closed. That's the difference between a policy on paper and one that proves itself. For your own repo: break-glass policy, ADR-002, workflow template.

The full suite has grown to 85 tests: 59 in the public engine repo, 26 in the Pro repo. Still deterministic, still no LLM in the scan path. And still dogfooding: the scan of our own repo runs in our own CI — every landing page change has to pass our own gate first. That exact setup has already blocked one of our own PRs. Working as designed; it's all in the changelog.

Two active open-source repos, two invisible characters:

Invisible in every diff and every review — but a different file for the model than for the human reading it. That's the documented invisibility trick, not a theoretical scenario. Both finds are byte-verified and were responsibly disclosed to the maintainers — with no public naming. If the maintainers want, there will be an update here.

Prices unchanged: Free, Pro $19/repo/month, Audit $499 (one-time), RedTeam $499/quarter.

── more in #ai-safety 4 stories · sorted by recency
── more on @agentguard 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/agentguard-update-op…] indexed:0 read:2min 2026-09-09 ·