Show HN: FKS2G – LLM-backed metrics for deciding how closely to review code

kmdupree1 pts0 comments

GitHub - kmdupr33/fks2g: A CLI for generating LLM-backed metrics for deciding how closely to review code · GitHub

/" data-turbo-transient="true" />

Skip to content

Search or jump to...

Search code, repositories, users, issues, pull requests...

-->

Search

Clear

Search syntax tips

Provide feedback

--><br>We read every piece of feedback, and take your input very seriously.

Include my email address so I can be contacted

Cancel

Submit feedback

Saved searches

Use saved searches to filter your results more quickly

-->

Name

Query

To see all available qualifiers, see our documentation.

Cancel

Create saved search

Sign in

/;ref_cta:Sign up;ref_loc:header logged out"}"<br>Sign up

Appearance settings

Resetting focus

You signed in with another tab or window. Reload to refresh your session.<br>You signed out in another tab or window. Reload to refresh your session.<br>You switched accounts on another tab or window. Reload to refresh your session.

Dismiss alert

{{ message }}

kmdupr33

fks2g

Public

Notifications<br>You must be signed in to change notification settings

Fork

Star

main

BranchesTags

Go to file

CodeOpen more actions menu

Folders and files<br>NameNameLast commit message<br>Last commit date<br>Latest commit

History<br>15 Commits<br>15 Commits

bin

bin

img

img

src

src

test

test

.gitignore

.gitignore

LICENSE

LICENSE

README.md

README.md

package-lock.json

package-lock.json

package.json

package.json

tsconfig.json

tsconfig.json

View all files

Repository files navigation

fks2g

Since code review is the bottleneck now, fks2g helps developers decide how closely to review code.

Its for the devs who have already tried this method of reviewing code:

And for devs who have realized that this code review strategy leads to a finger pointing situation when bugs or bad architecture gets shipped:

To inform how closely to review a code change, the CLI collects:

cosine similarity between file-name embeddings and configurable project text sources

an LLM judgment about whether the closest files are likely to change soon based on source documents

recent bug-fix commits classified by an LLM

file change frequency from git history

an LLM final risk assessment based on the collected evidence

Usage

npx fks2g analyze -- --repo ../react --github-repo facebook/react --model gpt-5.4-nano $(git -C ../react show --name-only --format='' | tr '\n' ' ') ">OPENAI_API_KEY=KEY> npx fks2g analyze -- --repo ../react --github-repo facebook/react --model gpt-5.4-nano $(git -C ../react show --name-only --format='' | tr '\n' ' ')

This analyzes the files from the most recent commit of the react repo if you've got it cloned on your machine. There's a --help flag.

Warning: 0.X software

This software is as ready for prime-time usage as its name suggests. I've only kicked the tires on it a bit with openai models. Theoretically, google, anthropic, and bedrock models are also supported.

About

A CLI for generating LLM-backed metrics for deciding how closely to review code

Resources

Readme

License

MIT license

Uh oh!

There was an error while loading. Please reload this page.

Activity

Stars

stars

Watchers

watching

Forks

forks

Report repository

Releases

No releases published

Packages

Uh oh!

There was an error while loading. Please reload this page.

Contributors

kmdupr33<br>Matt Dupree

Languages

TypeScript<br>99.6%

JavaScript<br>0.4%

You can’t perform that action at this time.

code fks2g review react json closely

Related Articles