fresh-eyes 0.2.0

Independent AI peer review of git diffs for Claude Code and other coding agents

fresh-eyes

Independent AI peer review of git diffs, designed for use alongside Claude Code (or any coding agent). Sends your latest changes to a different model so you get a second opinion with different blind spots from the one that wrote the code.

Install

uv tool install fresh-eyes

Or from a local checkout:

uv tool install --from . fresh-eyes

This installs two equivalent commands: fresh-eyes (canonical) and fe (typeable alias).

Setup

Export your Gemini API key (get one at https://aistudio.google.com/apikey):

export GEMINI_API_KEY=your-key-here

Activation

fresh-eyes is opt-in per repo, so it doesn't fire in every git repo you cd into. Enable it once per repo:

fresh-eyes --init      # enables fresh-eyes in this repo (writes .git/fresh_eyes_enabled)
fresh-eyes --disable   # disables it again

Running any other command in a non-activated repo prints a friendly message and exits without making API calls.

Usage

From inside an activated git repository:

fresh-eyes           # review commits since the last review (or HEAD~1 on first run)
fresh-eyes --full    # review the entire branch against the default branch
fresh-eyes --all     # one-time baseline: review the entire current codebase
fresh-eyes --staged  # review staged-but-uncommitted changes
fresh-eyes --reset   # interactively reset the marker (after a rebase, etc.)

fe is the short alias — fe --full works identically.

Claude Code integration

Copy the slash command files from this repo into your Claude Code commands directory:

cp commands/fresh-eyes.md commands/fe.md ~/.claude/commands/

You can now invoke /fresh-eyes or /fe in a Claude Code session. The command tells Claude to run the CLI, read its output, synthesize the findings against the current task context, and raise genuine concerns before continuing.

How it works

• Marker file: .git/fresh_eyes_last_<branch> stores the last reviewed commit per branch. Switching branches doesn't invalidate other branches' markers.
• Each run diffs from the marker to the HEAD captured at startup, sends it to Gemini, prints the review under a ## Gemini 2.5 Flash header, then advances the marker.
• Noise filtering: lockfiles, minified assets, and dist//build/ are excluded from the diff so they don't burn tokens.
• Size guard: bails out with a message (exit 0) if the diff exceeds ~10k estimated tokens.
• No synthesis in the tool: with multiple reviewers (coming in 0.2.0 with Mistral), the tool emits each reviewer's output verbatim under its own header. Claude Code does the synthesis using its task context.

Exit codes

Code	Meaning
0	Review ran successfully, OR diff was too large to send (the tool reports; it does not gate)
1	Marker commit missing (after rebase/force push), or git error
2	Missing/invalid GEMINI_API_KEY

License

MIT