Menu

#42 by GitHub stars

alibaba/open-code-review

Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.

Claude CodeCodexEngineeringData

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

plugins/open-code-review/skills/open-code-review/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Instructions only → After Local scripts

375f64cd6f67 → 8f9c8b771f65

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 375f64cd6f67

No earlier version was observed for comparison.

Compare on GitHub

plugins/open-code-review/skills/open-code-review-delegate/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Instructions only → After Local scripts

375f64cd6f67 → 8f9c8b771f65

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 375f64cd6f67

No earlier version was observed for comparison.

Compare on GitHub

skills/open-code-review/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Instructions only → After Local scripts

375f64cd6f67 → 8f9c8b771f65

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 375f64cd6f67

No earlier version was observed for comparison.

Compare on GitHub

skills/open-code-review-delegate/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Instructions only → After Local scripts

375f64cd6f67 → 8f9c8b771f65

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 375f64cd6f67

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit 8f9c8b771f65bed63a193e873f12cdffb050b748

git clone --filter=blob:none --no-checkout https://github.com/alibaba/open-code-review.git .hotskills/alibaba-open-code-review && git -C .hotskills/alibaba-open-code-review checkout --detach 8f9c8b771f65bed63a193e873f12cdffb050b748 # Copy each selected skill directory from .hotskills/alibaba-open-code-review into .claude/skills/<skill-name>/
git clone --filter=blob:none --no-checkout https://github.com/alibaba/open-code-review.git .hotskills/alibaba-open-code-review && git -C .hotskills/alibaba-open-code-review checkout --detach 8f9c8b771f65bed63a193e873f12cdffb050b748 # Copy each selected skill directory from .hotskills/alibaba-open-code-review into .agents/skills/<skill-name>/
49.6kGitHub stars
427stars in 7 days
4skills in this repository
48commits in 30 days

Heat

7.1
  • Star growth, last 7 daysAhead of 82% of tracked repositories
  • Star growth, last 24 hoursAhead of 84% of tracked repositories
  • Rank movement, last 7 daysAhead of 74% of tracked repositories
  • Commits, last 30 daysAhead of 90% of tracked repositories
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekAhead of 0% of tracked repositories

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Aug 2, 2026Nov 6, 202649,555

Individual skills in this repository

How it works

open-code-review

When your agent uses it

Performs AI-powered code review on Git changes using the `ocr` CLI from alibaba/open-code-review. Use when the user asks to review code, review a pull request, review staged/unstaged changes, review a commit, or compare branches for code quality issues. Produces line-level review comments and can automatically apply fixes when requested. With appropriate review rules, can detect various types of issues including bugs, security vulnerabilities, performance problems, and code quality concerns.

What it loads into context

Frontmatter

224 tokens

Always available to the agent

SKILL.md

3,037 tokens

When the skill is activated

Reference documents

4,572 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. Workflow
  2. Output Format
  3. Custom Review Rules
  4. Advanced Review Options
  5. Gotchas
  6. Validation
  7. Troubleshooting
  8. References

Files

  • ../../../../.claude-plugin/marketplace.jsonasset682 bytes
  • ../../claude-code/.claude-plugin/plugin.jsonasset295 bytes
  • ../../claude-code/commands/delegate-review.mddoc3,080 bytes
  • ../../claude-code/commands/delegate-review.mddoc3,080 bytes
  • ../../claude-code/commands/delegate-review.mddoc3,080 bytes
  • ../../claude-code/commands/delegate-review.mddoc3,080 bytes
  • ../../claude-code/commands/delegate-review.mddoc3,080 bytes
  • ../../claude-code/commands/review.mddoc1,674 bytes
  • ../../claude-code/commands/review.mddoc1,674 bytes
  • SKILL.mdcore12,891 bytes
  • SKILL.mdcore12,891 bytes
  • SKILL.mdcore12,891 bytes
  • SKILL.mdcore12,891 bytes
  • SKILL.mdcore12,891 bytes
  • SKILL.mdcore12,891 bytes
  • SKILL.mdcore12,891 bytes
Read SKILL.md

# Open Code Review

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

A skill for invoking [open-code-review](https://github.com/alibaba/open-code-review) (`ocr`) — an open-source AI code review CLI that reads Git diffs and generates structured, line-level review comments.

## Workflow

### Step 1: Gather Business Context

Analyze the review target (commits, branch, or changes) to extract concise business context. Pass this context via `--background` to improve review quality.
View the complete source on GitHub

Skills included

  • open-code-review
  • open-code-review-delegate
  • open-code-review
  • open-code-review-delegate

Repository facts

License
Apache-2.0
Created
May 18, 2026
Last pushed
Nov 5, 2026
Forks
3,631
Open issues
138
Project activity
Active

Rank over the last 12 weeks

Now #42 · best #40 · down 2 in 30 days

  1. #41 from Sep 30 to Oct 3
  2. #40 from Oct 4 to Oct 18
  3. #41 from Oct 19 to Oct 24
  4. #43 on Oct 25
  5. #41 on Oct 28
  6. #42 since Oct 29
22 earlier periods
  1. #80 on Aug 2
  2. #77 from Aug 7 to Aug 8
  3. #76 on Aug 9
  4. #77 from Aug 10 to Aug 11
  5. #78 from Aug 12 to Aug 13
  6. #79 from Aug 14 to Aug 16
  7. #80 from Aug 17 to Aug 23
  8. #79 from Aug 24 to Aug 26
  9. #80 from Aug 27 to Aug 29
  10. #81 from Aug 30 to Aug 31
  11. #80 from Sep 1 to Sep 12
  12. #79 on Sep 13
  13. #70 on Sep 14
  14. #64 on Sep 15
  15. #54 on Sep 16
  16. #50 on Sep 17
  17. #48 on Sep 18
  18. #47 from Sep 19 to Sep 20
  19. #46 from Sep 21 to Sep 22
  20. #44 from Sep 23 to Sep 24
  21. #43 from Sep 25 to Sep 26
  22. #42 from Sep 27 to Sep 29

Before you install

Local scripts

Automated signals, not a guarantee

Checked Nov 3, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 35 notes
  • plugins/open-code-review/claude-code/commands/delegate-review.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/open-code-review/claude-code/commands/delegate-review.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/open-code-review/claude-code/commands/delegate-review.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/open-code-review/claude-code/commands/delegate-review.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/open-code-review/claude-code/commands/review.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/open-code-review/skills/open-code-review/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/open-code-review/skills/open-code-review/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/open-code-review/skills/open-code-review/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/open-code-review/skills/open-code-review/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/open-code-review/skills/open-code-review/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/open-code-review/skills/open-code-review/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/open-code-review/skills/open-code-review-delegate/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/open-code-review/skills/open-code-review-delegate/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/open-code-review/skills/open-code-review-delegate/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/open-code-review/skills/open-code-review-delegate/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/open-code-review/skills/open-code-review-delegate/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/open-code-review/skills/open-code-review-delegate/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/open-code-review/skills/open-code-review-delegate/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/open-code-review/skills/open-code-review-delegate/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/open-code-review/skills/open-code-review-delegate/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
Show all 24 signals by file

plugins/open-code-review/skills/open-code-review-delegate/SKILL.md

  • Network accessline 15
    metadata:   author: alibaba   homepage: https://github.com/alibaba/open-code-review
  • Network accessline 16
    author: alibaba   homepage: https://github.com/alibaba/open-code-review   version: "1.0.0"
  • Network accessline 17
    homepage: https://github.com/alibaba/open-code-review

plugins/open-code-review/skills/open-code-review/SKILL.md

  • Network accessline 17
    metadata:   author: alibaba   homepage: https://github.com/alibaba/open-code-review
  • Network accessline 18
    author: alibaba   homepage: https://github.com/alibaba/open-code-review   version: "1.0.0"
  • Network accessline 19
    homepage: https://github.com/alibaba/open-code-review
  • Network accessline 30
    A skill for invoking [open-code-review](https://github.com/alibaba/open-code-review) (`ocr`) — an open-source AI code review CLI that reads Git diffs and generates structured, line-level review comments.
  • Network accessline 249
    ocr config set llm.url https://api.anthropic.com/v1/messages
  • Access to secretsline 250
    [Credential-related source omitted]
  • Network accessline 259
    - Full docs: https://github.com/alibaba/open-code-review
  • Network accessline 260
    - NPM package: https://www.npmjs.com/package/@alibaba-group/open-code-review
  • Network accessline 261
    - Issue tracker: https://github.com/alibaba/open-code-review/issues

skills/open-code-review-delegate/SKILL.md

  • Network accessline 15
    metadata:   author: alibaba   homepage: https://github.com/alibaba/open-code-review
  • Network accessline 16
    author: alibaba   homepage: https://github.com/alibaba/open-code-review   version: "1.0.0"
  • Network accessline 17
    homepage: https://github.com/alibaba/open-code-review

skills/open-code-review/SKILL.md

  • Network accessline 17
    metadata:   author: alibaba   homepage: https://github.com/alibaba/open-code-review
  • Network accessline 18
    author: alibaba   homepage: https://github.com/alibaba/open-code-review   version: "1.0.0"
  • Network accessline 19
    homepage: https://github.com/alibaba/open-code-review
  • Network accessline 25
    A skill for invoking [open-code-review](https://github.com/alibaba/open-code-review) (`ocr`) — an open-source AI code review CLI that reads Git diffs and generates structured, line-level review comments.
  • Network accessline 244
    ocr config set llm.url https://api.anthropic.com/v1/messages
  • Access to secretsline 245
    [Credential-related source omitted]
  • Network accessline 254
    - Full docs: https://github.com/alibaba/open-code-review
  • Network accessline 255
    - NPM package: https://www.npmjs.com/package/@alibaba-group/open-code-review
  • Network accessline 256
    - Issue tracker: https://github.com/alibaba/open-code-review/issues

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Signal confidence: 24 facts

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeNativeManifest .claude-plugin/marketplace.json.claude/skills/<skill-name>/
CodexNativeManifest AGENTS.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md plugins/open-code-review/skills/open-code-review/SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md plugins/open-code-review/skills/open-code-review/SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md plugins/open-code-review/skills/open-code-review/SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md plugins/open-code-review/skills/open-code-review/SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

You might also use

EliasOenal/term-cli

Interactive terminals for AI agents, built for what you can't --yes away. SSH+MFA, GRUB/U-Boot, debconf installers, SOL/serial consoles, fsck, cryptsetup, pdb/gdb, apt, certbot, p…

104GitHub stars

Jakeschincariol/replica-skill

Eleven free Claude skills that clone any app: reverse-engineer it, rebuild it, test it for bugs, then fix what its users hate. Free, MIT.

7.8kGitHub stars

JetBrains/thinkrail

Vibe code with pi in a lightweight, real IDE that customises itself around the way you work — The Vibe You Need

7.8kGitHub stars

agentscope-ai/agentscope-java

Build distributed, production-grade, long-running agents.

6.3kGitHub stars

vercel/eve

The Open Framework for Building Agents

5.8kGitHub stars

liustack/modlens

Plug-in vision for text-only models. Hard rule: when a file path or URL with an image extension (.png, .jpg, .jpeg, .webp, .gif, .heic, .heif) appears anywhere in the conversation…

4.8kGitHub stars

Explore alternatives and comparisons

Add this badge to your README

It updates every night and links to this page.

alibaba/open-code-review: #42 on hotskills, 49.6k stars

[![alibaba/open-code-review on hotskills](https://hotskills.dev/badge/alibaba-open-code-review.svg)](https://hotskills.dev/skill/alibaba-open-code-review/)