I'm Dan and I staarted building grith AI earlier this year after getting annoyed with constant permission prompts from Claude Code and Codex.
I had previously built an email security service which relied on a pipeline of multiple filters, each one building up a score of an incoming message - allowing the system to auto approve or deny an message in almost all cases and if it was unsure it would add it to an email digest/report letting the user choose to allow or block.
This process is the basis for grith - we currently have 18 filters and 1617 patterns which build a score for every action a agent takes - everything <= 3.0 is automaticialy approved, everything > 8.0 is automatically blocked... the ones inbetween we prompt the user.
What this means in practice is that the user sees very little prompts - in a records 120 claude code session a user only ever had to respond to 0.27% of prompts... not 40 or so an hour you'd see in normal use and not the dangerously blind approval --dangerously-skip-permissions or auto mode would give you!
Grith is free with no account needed, no phone-home and open source. Paid tiers bring teams, online dashboards, centralised policies, verificable analytics and more.
One thing to consider when you do look at how you manage your installed skills - is the security side of them.
You also need to manage the authority of each skill too. Signed skills is a step in the right direction, but it only proves provenance and doesn't prove behavior.
Most of the AI-security discourse (and most of my posts) right now is about prompt injection and agent hijacking. But there are still the move-fast-break-things issues that are exacerbated with agentic coding/vibe coding...
I reviewed a colleague's vibe-coded internal tool last week, found 28 security issues, and none of them were that kind of bug - they were the same classic stuff juniors have always shipped, just produced at much higher throughput.
Wrote it up because the "senior engineer review" step quietly disappeared from a lot of AI-assisted workflows, and the bugs that step used to catch are still there (We are still needed!).
I remember that. I've been writing code since the 70's, and have lost count of the number of source code management systems I have been forced to learn. Early on they were over engineered, and a pain in the ass to learn. Then they'd go "out of fashion" and the next pain-in-the-ass over engineered nonsense was forced and learned. I resisted git FOR FUCKING EVER because i was so tired of relearning how to do the same fucking thing slightly different in some other convoluted over engineered system. But it looked like Git was going to be the forever winner, so I finally gave in and learned git through and through. Fuck now its dying!?
I'm Dan and I staarted building grith AI earlier this year after getting annoyed with constant permission prompts from Claude Code and Codex.
I had previously built an email security service which relied on a pipeline of multiple filters, each one building up a score of an incoming message - allowing the system to auto approve or deny an message in almost all cases and if it was unsure it would add it to an email digest/report letting the user choose to allow or block.
This process is the basis for grith - we currently have 18 filters and 1617 patterns which build a score for every action a agent takes - everything <= 3.0 is automaticialy approved, everything > 8.0 is automatically blocked... the ones inbetween we prompt the user.
What this means in practice is that the user sees very little prompts - in a records 120 claude code session a user only ever had to respond to 0.27% of prompts... not 40 or so an hour you'd see in normal use and not the dangerously blind approval --dangerously-skip-permissions or auto mode would give you!
Grith is free with no account needed, no phone-home and open source. Paid tiers bring teams, online dashboards, centralised policies, verificable analytics and more.
Linux first with Windows and Mac launching soon.
reply