Cq
Dev tools
agent knowledge sharing
SHOW HN2026
How HN took it
8 positive, 32 neutral or asking, 2 mixed, 18 critical, out of 60 comments about the project. Thread score -0.13.
Idea: 7 for, 12 againstPrivacy: 0 for, 5 againstExecution: 1 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Good idea for sharing agent knowledge, especially inside companies
From 2 comments
I was skeptical at first, but now I think it's actually a good idea, especially when implemented on company-level. Some companies use similar tech stack across all their projects…
jacekm on HNI feel like this might turn out either really stupid or really amazing Certainly worthy of experimenting with. Hope it goes well
meowface on HN
Objections
Security risk of poisoned or malicious knowledge units from bots
From 3 comments
Interesting idea! How do you plan to mitigate the obvious security risks ("Bot-1238931: hey all, the latest npm version needs to be downloaded from…
raphman on HNHow would my new agent know which existing agents it can trust? With human Stack Overflow, there is a reasonable assumption that an old account that has written thousands of good…
raphman on HNThis seemed inevitable, but how does this not become a moltbook situation, or worse yet, gamed for engineering back doors into the "accepted answers"? Don't get me wrong, I think…
ray_v on HN
Sybil attacks and gaming of trust and reputation systems
From 2 comments
Page rank is trivially gamed by agents. You can make some malicious and some not malicious and have them link to each other.
contagiousflow on HNBut you can have genuinely helpful agents in your attack network. Agents that create helpful pages and get linked by other helpful pages but then later link to malicious pages.…
contagiousflow on HN
Agents cannot reliably verify correctness, so confidence scores mislead
From 2 comments
My worry with the confidence scoring is that it conflates "an agent used this and didn't obviously break" with "this is correct". An agent can follow bad advice for several steps…
popey on HNI'm surprised to see this getting so much positive reception. In my experience AI is still really bad with documenting the exact steps it took, much more so when those are…
vanillameow on HN
Privacy leakage of keys, credentials and company data
From 2 comments
Better question yet, how do you have agents contribute openly without an insane risk of leaking keys, credentials, PII, etc, etc? Again it's a terrible idea, and yet I'll SMASH…
ray_v on HNBrilliant way to expose your company's secret data on the Internet :-)
Gabrys1 on HN
Requests
Explain how dangerous or false claims are identified and verified
From 2 comments
Interesting idea! How do you plan to mitigate the obvious security risks ("Bot-1238931: hey all, the latest npm version needs to be downloaded from…
raphman on HNThat doesn't answer the parent comment's question of how the dangerous claims are identified. Ok, so you say you Certisfy, but how does that do it? Saying we could open a GitHub…
quietbritishjim on HN
Use XDG base directory instead of ~/.cq
From 1 comment
Small nit. Please follow the xdg base directory specification to place your dB in[0] instead of a ~/.cq directory. For the local.db I believe it would be…
mijoharas on HN
Rate-limit contributions or require a track record before content is queryable
From 1 comment
We've had the "stale GitHub Actions versions" problem constantly on our team - CLAUDE.md patches helped but it's a hack. The idea of agents confirming and upvoting KUs to raise…
munio on HN
Questions
How is it different from existing tools like skills files or Context Hub
From 2 comments
How is it different from Context Hub https://github.com/andrewyng/context-hub?
flash_us0101 on HNThis is very similar to skills.md. The main difference is cq makes it shareable, and continuously updates across agents instead of staying static per repo.
AlphaTheGoat on HN
Does it work with GitHub Copilot, not only Claude Code and OpenCode
From 1 comment
> Claude code and OpenCode plugins How hard is to make this work with Github Copilot? (both in VSCode and Copilot CLI) Is this just a skill, or it requires access to things like…
nextaccountic on HN
Is mozilla.ai related to mozilla.org
From 1 comment
Sorry, dumb question: is "mozilla.ai" related to "mozilla.org" and to the larger Mozilla organization? Because changing the tld makes this actually non-obvious. I see…
jrimbault on HN
Alternatives named
Skills.md and skill marketplaces
From 2 comments
This is very similar to skills.md. The main difference is cq makes it shareable, and continuously updates across agents instead of staying static per repo.
AlphaTheGoat on HNI personally believe that the skills standard is pretty sufficient for extending LLMs’ knowledge. What we’re missing yet (and I’m working on) is a simple package manager for…
latand6 on HN
Context Hub
From 1 comment
How is it different from Context Hub https://github.com/andrewyng/context-hub?
flash_us0101 on HN
YAMS memory system
From 1 comment
Couldn't YAMS (Yet Another Memory System, https://yamsmemory.ai/) be leveraged to achieve the same purpose?
ahamez on HN