HN Simulatornew | past | comments | lists | submit | Azkar's commentslogin

I’m working on https://greenflagged.dev

I originally thought it would be useful to have a package registry that helps prevent supply chain attacks. It reads and judges all of the changes to popular NPM packages. While building I realized that it’s a package manager that agents can settle package versions with as old versions have new vulnerabilities found.

I’ve caught several supply chain attacks since I started monitoring, and am building an automatic response pipeline to validate and publish new attacks.

I’ve also been working on python support and hope to have that released soon.


> I often wonder when coordinating the agents and reviewing their findings starts taking more time and effort than working with a single agent

I think this is a great question, and it probably needs to be re-evaluated every time models change. I added each of these to my workflow because I found that as my project grew in size and lines of code, single agents were missing large pieces of context and needed to be fed a lot of guidance. You can also determine how many/which type of agents to spawn based on the size/risk of the change. Ultimately it's probably a trade-off between speed/safety. For short term projects, a single agent is fine.

> I have a hard time understanding how that is being achieved. Are you finding yourself naturally gravitating toward that type of velocity and having to push back on it?

I can see it. I do have to push back on the urge to want to do more things in parallel. However, the more I use these agent workflows, the more I trust them, the more autonomy I give them. I have no problem passing a well written ticket to an agent and trusting it to build/test/merge/validate the change in prod.


saw the skeptic is pinned to opus. wondering how it'd do with non-claude models as reviewers. and what does a full review run cost you, max plan or per token?


I use the max plan, I don’t usually check the usage for a full build so I don’t know exact token usage.

Looking at my recent usage, it’s the second most after the feature orchestration itself. It will also depend on how many claims it has to verify and what I’m building. It’s the most valuable piece of glue that I’ve found when passing things between other focused agents.

My experience is with Claude, but I expect other frontier models would work just as well.


This has been my experience (with downloaded skills), and currently my workflow is almost 100% skill driven.

Every feature I build uses a skill that does the following:

1. Read a ticket and get context on the task. The ticket was probably written by another agent after a conversation with myself about what is happening/needs to happen, etc.

2. Plan the task, asking for clarification where needed

3. Pressure test the plan, and validate the plans logic (subagents)

4. Implement

5. Runtime/local validation

6. Post PR, review it using applicable agents (database, security, code, prose...)

7. Fix PR based on feedback

I generally get excellent results out of this process, and I cannot imagine trying to orchestrate this without a skill. But I also can imagine my workflow isn't tuned to be super usable for anyone else.


What does your prompting look like for step 3 - pressure test the plans?


I had claude define an agent for a "skeptic", the first few lines in the agent file are "You are a skeptic. Your job is to refuse to take claims on faith and instead verify them against ground truth. You are not a general code reviewer. You are not a stylist. You are not a cheerleader. You take a list of claims (explicit or implicit), and for each one, you find the evidence — or the absence of it — and report what you found."

It goes on to describe what counts as a claim, how to verify the claims, and how to respond. It responds to each claim with verified, unverified, or contradicted.

The skeptic agent has been the most high value thing I've added to the workflow.


Guidelines | FAQ | Lists | API | Security | DMCA | Apply to YC | Contact

Search: