Skip to content
Skillpedia
Testing47k · #4694

open-code-review-delegate

Lets your agent perform code reviews directly, using its own AI capabilities. It's useful when the main agent should control the review process.

What it does

This tool helps review programming code. It identifies which parts of the code need checking and which rules to follow, leaving the detailed analysis to the main agent's intelligence. It's useful when the main agent should be the one performing the review.

When to use it

  • ✓When you want the main AI agent to analyze the code.
  • ✓To check changes in specific code or a set of files.
  • ✓When comparing different code versions for review.

Example of what to ask your AI

“Review the code for me, focusing on security and performance.”

Want more? Open the sections below.

How to use

The easiest way: copy the message below and paste it into Claude, ChatGPT, Cursor or any AI. It reads the skill and follows the instructions.

Skill link

https://github.com/alibaba/open-code-review/blob/main/plugins/open-code-review/skills/open-code-review-delegate/SKILL.md

Ready-to-paste message

Use this skill to help me: https://github.com/alibaba/open-code-review/blob/main/plugins/open-code-review/skills/open-code-review-delegate/SKILL.md Read the SKILL.md file at that link and follow its instructions for my task.
How it works

First, the tool identifies the files to be reviewed and the applicable rules. Then, it gets the differences (what changed) between code versions. Finally, the main agent uses this information to perform the review.

Installation

Easiest way: copy the skill link and paste it into Claude, ChatGPT or Cursor asking it to follow the instructions.

In the terminal (Claude Code, Codex, Cursor), in your project folder:

npx skills add alibaba/open-code-review --skill open-code-review-delegate

Or download just the file:

curl -L https://raw.githubusercontent.com/alibaba/open-code-review/main/plugins/open-code-review/skills/open-code-review-delegate/SKILL.md -o SKILL.md
Technical content (original SKILL.md)

Original text by the author, straight from GitHub.

Open Code Review — Delegation Mode

This Codex plugin skill intentionally mirrors the canonical skill at skills/open-code-review-delegate/SKILL.md. Keep both files synchronized when updating OCR delegation instructions; a symlink is avoided because plugin installs may only materialize the plugin subtree.

A skill for performing AI code review where OCR provides deterministic engineering (file filtering, rule resolution) and the host agent performs the actual review using its own intelligence and tools.

Workflow

Step 1: Preview — Determine What to Review

ocr delegate preview --format json [--from <ref> --to <ref>] [--commit <hash>] [--exclude <patterns>]

This outputs:

  • mode (workspace / range / commit)
  • from / to / commit / merge_base — ref metadata for constructing git commands
  • Reviewable file list — paths, status, insertions/deletions
  • Excluded files — with exclusion reason

Common invocations:

Scenario Command
Workspace changes ocr delegate preview
Branch comparison ocr delegate preview --from main --to feature
Single commit ocr delegate preview -c abc123

Step 2: Get Rules for Files

ocr delegate rule --format json <path1> <path2> ...

Pass the reviewable file paths from Step 1. Output is grouped by rule content — files sharing the same rule appear under one group, avoiding repetition.

Step 3: Get Diffs

Choose the diff command using the mode and refs from Step 1. Use git --no-pager for every Git call during the review.

The diff commands disable external diff programs, text conversion, and color to produce plain patches.

Range mode (merge_base provided in preview output):

git --no-pager diff --no-ext-diff --no-textconv --no-color <merge_base>..<to> -- "<path>"

Commit mode:

git --no-pager show --no-ext-diff --no-textconv --no-color <commit> -- "<path>"

Workspace mode:

# Tracked files
git --no-pager diff --no-ext-diff --no-textconv --no-color HEAD -- "<path>"
# New untracked files — read directly (entire file is new code)
cat "<path>"

To read context:

git --no-pager log --no-color --oneline -- "<path>"
git --no-pager blame --no-textconv -- "<path>"
git --no-pager show --no-ext-diff --no-textconv --no-color "<ref>:<path>"

For large diffs, add --output="<absolute-diff-file>" to the command for the selected mode. Choose a unique absolute path outside the repository and create its parent directory. Use the same path in file-reading tool calls:

git --no-pager diff --no-ext-diff --no-textconv --no-color --output="<absolute-diff-file>" <merge_base>..<to> -- "<path>"

After Git exits with code 0, read and review the entire file in chunks, then remove it. If Git fails or times out, retry or record skipped with the error. Check unexpectedly empty output against a fresh preview.

Step 4: Review Each File

Create a checklist containing every reviewable_files entry. For each reviewable file:

Use (path, status) as the checklist identity. Workspace mode can report the same path twice when a staged deletion is followed by an untracked recreation.

  1. Get its diff (Step 3)
  2. Consult its Rule Group (from Step 2) for the review checklist
  3. Conduct a thorough review, using appropriate context tools as needed
  4. Mark the file reviewed, or skipped with a concrete reason

For large changes, review in bounded batches grouped by shared rules and diff size. Do not stop after finding the first high-severity issue.

Step 5: Format Output

Each comment must follow this structure:

Field Type Required Description
path string yes Relative file path
content string yes Review comment describing the issue
start_line integer no Start line in the new file
end_line integer no End line in the new file
category enum no bug, security, performance, maintainability, test, style, documentation, other
severity enum no critical, high, medium, low

Step 6: Classify and Report

Before reporting, verify that every previewed file is accounted for. Include total_files, reviewed_files, skipped_files, and coverage_rate in the summary. A skipped file must include its reason.

Group findings by severity:

  • Critical/High: Bugs, security issues, data loss risks — always report

…

FAQ

What does 'delegation' mean?

It means the tool delegates the main analysis task to the primary AI agent, focusing only on organizing and preparing the necessary information for that analysis.

Do I need programming knowledge to use this?

No, the tool is designed for simple use. You just need to indicate what you want to review.

What are 'rules'?

These are guidelines or standards that the code should adhere to, such as best practices for security or programming style.

Details

Original description by the author

Delegation mode for open-code-review (OCR). Instead of OCR calling an LLM endpoint, this skill instructs the host agent to perform the code review itself, using OCR only for deterministic engineering: file selection and rule resolution. Use when the host agent should drive the review with its own LLM capabilities.

repo: alibaba/open-code-review

Popularity

GitHub stars
47k
Ranking position
#4694
License
Apache-2.0
Updated
10/15/2026

Is this skill useful?

0

Sign in to vote.

Comments

  • …

More skills from this repository

Similar skills