Open Code Review

Open Code Review

A skill for invoking open-code-review (ocr) — an open-source AI code review CLI that reads Git diffs and generates structured, line-level review comments.

Prerequisites check

Before starting a review, verify the environment:

# 1. Check the CLI is installed
which ocr || echo "NOT INSTALLED"

# 2. Verify LLM connectivity
ocr llm test

If ocr is not installed, install it first:

npm install -g @alibaba-group/open-code-review

If ocr llm test fails, the user must configure an LLM. Guide them with one of these options:

Option A — Environment variables (highest priority, recommended for CI):

export OCR_LLM_URL=https://api.anthropic.com/v1/messages
export OCR_LLM_TOKEN=<api-key>
export OCR_LLM_MODEL=claude-opus-4-6
export OCR_USE_ANTHROPIC=true

Option B — Persistent config:

ocr config set llm.url https://api.anthropic.com/v1/messages
ocr config set llm.auth_token <api-key>
ocr config set llm.model claude-opus-4-6
ocr config set llm.use_anthropic true

Stop here and ask the user to provide credentials — never invent or hardcode API keys.

Workflow

Step 1: Gather Business Context

Before running the review, inspect the review target (commits, branch, working copy) and synthesise a short --background string that captures the intent of the changes. This improves review quality by giving the LLM context about what the code is trying to achieve.

Step 2: Run Code Review

• Preview mode: use --preview or -p to preview which files will be reviewed without running the LLM
• Installation: if ocr command is not found, install it by running npm i -g @alibaba-group/open-code-review

Common invocation patterns:

Output mode:

• Always use --audience agent to suppress progress UI and emit only the final summary

Step 3: Classify and Report

Group the JSON comments into High / Medium / Low using the rubric below, then render a Markdown summary.

Nitpicks and likely false positives are silently dropped.

Step 4: Fix

If the user said "review and fix" (or similar), apply safe fixes to High/Medium items inline. Otherwise ask before touching the code.

Output Format

Each comment follows this structure:

Custom Review Rules

OCR supports custom review rules via .ocr-rules.yaml in the repo root. Rules can target specific file patterns and define review checklists. See the Review Rules docs for the full schema.

Gotchas

• LLM must be configured first — ocr review will fail loudly if no LLM is reachable. Always run ocr llm test before the first review.
• Working directory matters — ocr review operates on the Git repo at the current directory. Use --repo /path/to/repo to run from elsewhere.
• Untracked files are reviewed in workspace mode — running bare ocr review includes staged, unstaged, and untracked changes. Stage selectively if you want narrower scope.
• Large diffs may hit token limits — files with very large diffs may be truncated. The default MAX_TOKENS is 58888 per request.
• Plan phase triggers at 50 lines — diffs exceeding 50 changed lines run an extra risk-analysis phase before main review. This adds latency but improves quality.
• Don't pass --audience human — it streams progress UI that pollutes output. Always use --audience agent.

Validation

After the review completes, verify success by checking:

1. The command exited with code 0
2. Comments were generated (or "No comments generated" message appears)
3. Warnings (if any) are displayed in stderr

If errors occurred, check the stderr warnings for details about which files failed and why.

References

• Full docs: https://github.com/alibaba/open-code-review
• NPM package: https://www.npmjs.com/package/@alibaba-group/open-code-review
• Issue tracker: https://github.com/alibaba/open-code-review/issues