DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to feed a diff review as JSON to a coding agent with Jev Review

Print the change review as JSON so an agent can triage the findings against the code.

Who it is forA developer using an AI coding agent who wants the agent to act on review findings rather than read them by hand.

The problemAgents need structured input, and a plain-text review is hard to parse reliably.

The outcomeA JSON review of the current diff that the agent can use to decide which findings to fix, dismiss, or investigate.

What you need first

  • Node.js 24 or newer
  • Git installed and a Git repository to review
  • A TypeSafe API key from https://console.typesafe.ai/settings/keys

Steps

  1. Install Node.js 24 or newer and Git, then add TYPESAFE_API_KEY to .env.
  2. Run npm install in the Jev Review folder.
  3. Run npm run review:changes -- /path/to/git/repository and save the printed JSON to a file. (inferred, check the README)
  4. Give the JSON file to your coding agent with instructions to check each finding against the cited hunk.

Prompt for your agent

In the jev-review repo, run `npm run review:changes -- <path to git repository>` and capture the JSON output. For each finding, open the cited diff hunk in the target repository and label it as confirmed, unclear, or false positive. Verify the labels by re-reading the code before you change anything.

Caveat. The README calls findings review prompts, so an agent should confirm each one in the code and not apply fixes automatically.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page