Hacker News: claudiacsf

Show HN: Verity – self-healing review gate for Claude Code

claudiacsf — Fri, 26 Jun 2026 12:27:05 +0000

Hi folks,

We built what we think the next generation of code review looks like. It's an adversarial, self-healing gate for coding agents that repairs the code on every run, so only clean and secure code moves forward.

Here's a short demo https://www.youtube.com/watch?v=vsq_cHoZCnk

The next agent run also starts smarter than the last thanks to a built-in memory, and because of that agent costs start to stabilize.

It's completely free while in beta. We're looking for testers doing serious agentic engineering to help shape the roadmap.

Install takes about two minutes, and you'll see your first gated review on your next agent run. Give it a spin:

npm install -g @codacy/verity-cli && verity init

Comments URL: https://news.ycombinator.com/item?id=48685853

Points: 4

# Comments: 0

New comment by claudiacsf in "Code review is dead. Long live code review"

claudiacsf — Thu, 25 Jun 2026 16:51:11 +0000

Agreed the move is AI reducing what you review, not adding to it. What's also needed is a process for classifying changes by risk so the low risk PRs get the automated gates while a human looks only at the high risk one that actually need it. And then enforcing that the same way across every repo.

New comment by claudiacsf in "Show HN: OpenKnowledge – open source AI-first alternative to Obsidian/Notion"

claudiacsf — Thu, 25 Jun 2026 16:12:56 +0000

I'm a sucker for pretty UIs. I already have a company-mandated knowledge base tool, Slite, can they be used together?

New comment by claudiacsf in "Apple raises prices of MacBooks, iPads"

claudiacsf — Thu, 25 Jun 2026 16:03:17 +0000

So this is how Apple makes up for the margins on the Neos.

Code review is dead. Long live code review

claudiacsf — Thu, 25 Jun 2026 16:00:00 +0000

Article URL: https://blog.codacy.com/code-review-is-dead-why-ai-generated-code-needs-verification-not-human-approval

Comments URL: https://news.ycombinator.com/item?id=48675372

Points: 5

# Comments: 2

New comment by claudiacsf in "Show HN: I rebuilt the only parts of my IDE I use, in Rust, over a weekend"

claudiacsf — Tue, 23 Jun 2026 13:40:53 +0000

Oh man, that's a great idea. Well done.

The Tokenminning Manifesto

claudiacsf — Fri, 19 Jun 2026 09:42:31 +0000

Article URL: https://www.tokenminning.com/

Comments URL: https://news.ycombinator.com/item?id=48596705

Points: 2

# Comments: 0

New comment by claudiacsf in "Agentic AI PRs sit in the review queue 5.3x longer than unassisted ones"

claudiacsf — Wed, 17 Jun 2026 12:49:39 +0000

In teams where there is downward pressure to reduce the rigorousness of PRs there shouldn't be much of a bottleneck problem. They've solved it by lowering the bar. The article is for the teams who have decided the bug and incident cost of doing that isn't worth it, and now have to absorb the volume anyway.

>But as AI generates more of the code, the industry will likely move toward more radical review models.

>>Quit dancing around it and just advocate pushing to main. The PR model is to have a quality gate.

The dancing is IMO a reasonable analysis of the state of the code review today. Yes, there are systems in the works but today there isn't yet a good enough system of automated checks to simply let code through. Because then this happens https://pages.faros.ai/hubfs/AI_Engineering_Report_2026_The_...

New comment by claudiacsf in "Agentic AI PRs sit in the review queue 5.3x longer than unassisted ones"

claudiacsf — Tue, 16 Jun 2026 11:24:27 +0000

Fair. TL;DR:

The goal with the article is to explain what tools can be employed to tackle the PR bottleneck and where humans are still needed - at this point in time. Code quality and security platforms like Codacy (here's the service) can automate away many baseline checks (SAST, test coverage, complexity, duplication, linters, etc). This provides deterministic analysis that is the same every time, unlike pure AI code reviewers. But there's very much still room for AI-assisted reviews. AI is very good at identifying what has changed, grouping findings by severity and helping the human reviewer focus their attention. After these 2 passes, human attention can be reserved for the important judgement calls. "Human reviewers concentrate on judgment rather than scanning for issues that tools can detect consistently."

Codacy does both layers, the deterministic checks that have to be repeatable and auditable, and the AI on top. This cuts review time without lowering coding standards.

Agentic AI PRs sit in the review queue 5.3x longer than unassisted ones

claudiacsf — Tue, 16 Jun 2026 10:29:55 +0000

Article URL: https://blog.codacy.com/ai-breaking-code-review-how-engineering-teams-survive-pr-bottleneck

Comments URL: https://news.ycombinator.com/item?id=48553126

Points: 5

# Comments: 4

Show HN: Codacy Skills for Claude, Codex, Copilot, etc.

claudiacsf — Wed, 10 Jun 2026 11:57:04 +0000

Codacy is a code quality and security platform that helps eng teams enforce coding standards against their AI generated code.

They just launched agent skills and a cloud CLI, which allows Claude etc. to handle everyday tasks without using the UI

E.g. prompt: "PR 42 is failing the gate, fix what's real, add the tests, ignore the false positives with a reason, re-run."

The analysis runs server-side and burns no agent tokens.

Comments URL: https://news.ycombinator.com/item?id=48474980

Points: 1

# Comments: 0

New comment by claudiacsf in "Y Combinator's CEO says he ships 37,000 lines of AI code per day"

claudiacsf — Wed, 10 Jun 2026 09:56:44 +0000

Nobody can ship better than me. My ships are tremendous.

New comment by claudiacsf in "Y Combinator's CEO says he ships 37,000 lines of AI code per day"

claudiacsf — Fri, 05 Jun 2026 19:20:22 +0000

I could ship double.

Y Combinator's CEO says he ships 37,000 lines of AI code per day

claudiacsf — Fri, 05 Jun 2026 16:15:47 +0000

Article URL: https://www.fastcompany.com/91520702/y-combinator-garry-tan-agentic-ai-social-media

Comments URL: https://news.ycombinator.com/item?id=48414607

Points: 9

# Comments: 7

If you've ever had to defend paying down tech debt vs. feature work

claudiacsf — Fri, 05 Jun 2026 13:55:08 +0000

Article URL: https://blog.codacy.com/complete-guide-to-technical-debt-tracking-for-engineering-leaders

Comments URL: https://news.ycombinator.com/item?id=48412627

Points: 4

# Comments: 0

New comment by claudiacsf in "Claude Code is thinking too much"

claudiacsf — Tue, 14 Apr 2026 13:35:21 +0000

I'm a regular user and did not notice a difference.

New comment by claudiacsf in "Ask HN: I quit my job over weaponized robots to start my own venture"

claudiacsf — Tue, 14 Apr 2026 12:55:38 +0000

Not helpful if all detractors leave a company that's going down a dangerous path, leaving all the trigger happy peeps to follow their worst instincts. But understandable regardless.

New comment by claudiacsf in "Show HN: EU Leadership – Live API data site comparing Europe to the world"

claudiacsf — Wed, 01 Apr 2026 18:07:14 +0000

Nevermind that a huge portion of the US GDP is just them making health care a business. Not to mention warfare.

Geoff Huntley, creator of the Ralph loop, goat farmer, prophet

claudiacsf — Mon, 19 Jan 2026 23:12:31 +0000

Article URL: https://www.youtube.com/watch?v=lQ2ihlUzlfs

Comments URL: https://news.ycombinator.com/item?id=46685888

Points: 3

# Comments: 0

New comment by claudiacsf in "American importers and consumers bear the cost of 2025 tariffs: analysis"

claudiacsf — Mon, 19 Jan 2026 17:46:04 +0000

Trump's owners greenlit his pet policy because they knew exactly who'd pay: not them.