VerifiedPlugin
Testing
skill-up
An evaluation and evolution tool for Agent Skills.
3 skills
@alibabaDevelopment
Plugin
alibaba-open-code-review
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.
Plugin Signal83/100Strong
maintained100
capable48
documented100
adopted91
Install on Claude Code
> /plugin marketplace add alibaba/open-code-review> /plugin install open-code-review@open-code-review
What's inside
Skills
4/open-code-review-delegateDelegation 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/open-code-reviewPerforms 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/open-code-review-delegateDelegation 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/open-code-reviewPerforms 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
Commands
5/commitPlease summarize your current changes, generate a commit message in English, then add and commit./open-code-reviewInvoke the professional code review Agent CLI tool OpenCodeReview (OCR) to review current code changes, and let the Agent autonomously decide whether to apply fixes./tagCreate an annotated git tag with an auto-generated summary of changes since the last tag./delegate-reviewRun OCR in delegation mode — OCR handles file selection and rules, the host agent performs the actual review./reviewRun OpenCodeReview (OCR) to review code changes and autonomously apply fixes.
README
1What is Open Code Review?
Open Code Review is an AI-powered code review CLI tool. It originated as Alibaba Group's internal official AI code review assistant — over the past two years, it has served tens of thousands of developers and identified millions of code defects. After thorough validation at massive scale, we incubated it into an open source project for the community. Simply configure a model endpoint to get started.
It reads Git diffs, sends changed files to a configurable LLM via an agent with tool-use capabilities, and generates structured review comments with line-level precision. The agent can read full file contents, search the codebase, inspect other changed files for context, and produce deep reviews — not just surface-level diff feedback. Beyond diff review, ocr scan reviews entire files for auditing unfamiliar codebases or directories that have no meaningful diff.
Visit the official website for more details.
Benchmark
Compared to general-purpose agents (Claude Code), Open Code Review achieves significantly higher Precision and F1 with the same underlying model, while consuming only ~1/9 of the tokens and completing reviews faster. Note that its Recall is lower than general-purpose agents — a deliberate trade-off favoring precision over noise.
A real-world code review benchmark built from 50 popular open-source repositories, 200 real Pull Requests, and 10 programming languages — cross-validated by 80+ senior engineers (1,505 annotated ground-truth issues).
| Metric | What it measures | Why it matters |
|---|---|---|
| F1 | Harmonic mean of precision and recall | Best single number for overall review quality |
| Precision | Proportion of reported issues that are real defects | Higher = fewer false alarms to triage |
| Recall | Proportion of real defects that are found | Higher = fewer issues slip through review |
| Avg Time | Wall-clock time per review | Matters for CI pipeline latency |
| Avg Token | Total tokens consumed per review | Directly impacts API cost |
Why Open Code Review?
The Problem with General-Purpose Agents
If you've used general-purpose agents like Claude Code with Skills for code review, you've likely encountered these pain points:
- Incomplete coverage — On larger changesets, agents tend to "cut corners," selectively reviewing only some files and missing others.
- Position drift — Reported issues frequently don't match the actual code location, with line numbers or file references drifting off target.
- Unstable quality — Natural-language-driven Skills are hard to debug, and review quality fluctuates significantly with minor prompt variations.
The root cause: a purely language-driven architecture lacks hard constraints on the review process.
Core Design: Deterministic Engineering × Agent Hybrid
Open Code Review's core philosophy is to combine deterministic engineering with an agent, each handling what it does best.
Deterministic Engineering — Hard Constraints
For review steps that must not go wrong, engineering logic — not the language model — guarantees correctness:
- Precise file selection — Determines exactly which files need review and which should be filtered, ensuring no important change is missed.
- Smart file bundling — Groups related files into a single review unit (e.g.,
message_en.propertiesandmessage_zh.propertiesare bundled together). Each bundle runs as a sub-agent with isolated context — a divide-and-conquer strategy that stays stable on very large changesets and naturally supports concurrent review. - Fine-grained rule matching — Matches review rules to each file's characteristics, keeping the model's attention sharply focused and eliminating information noise at the source. Compared to purely language-driven rule guidance, template-engine-based rule matching is more stable and predictable.
- External positioning and reflection modules — Independent comment-positioning and comment-reflection modules systematically improve both the location accuracy and content accuracy of AI feedback.
Agent — Dynamic Decision-Making
The agent's strengths are concentrated where they matter most — dynamic decisions and dynamic context retrieval:
- Scenario-tuned prompts — Prompt templates deeply optimized for code review, improving effectiveness while reducing token consumption.
- Scenario-tuned toolset — Distilled from deep analysis of tool-call traces in large-scale production data — including call frequency distributions, per-tool repetition rates, and the impact of new tools on the overall call chain — resulting in a purpose-built toolset that is more stable and predictable for code review than a generic agent toolkit.
How to Use
Prerequisites
- Git >= 2.41 — Open Code Review relies on Git for diff generation, code search, and repository operations.
CLI
Install
npm install -g @alibaba-group/open-code-review
After installation, the ocr command is available globally.
For other installation methods (install script, GitHub Release binary, from source), see Installation.
Quick Start
1. Configure LLM
You must configure an LLM before reviewing code, unless you use Delegation Mode.
ocr config provider # Select a built-in provider or add a custom one
ocr config model # Pick a model for the active provider
The interactive UI guides you through provider selection, API key entry, and model configuration, then automatically tests connectivity.
For CLI setup, environment variables, custom providers, and other advanced configuration, see Configuration.
2. Review
cd your-project
# Workspace mode — review all staged, unstaged, and untracked changes
ocr review
# Branch range — reviews feature-branch's changes since it diverged from main (merge-base mode)
ocr review --from main --to feature-branch
# Single commit
ocr review --commit abc123
# Resume an interrupted range or commit review
ocr session list
ocr review --from main --to feature-branch --resume <session-id>
# Full-file scan — review whole files instead of a diff (no git history needed)
ocr scan # scan the entire repository
ocr scan --path internal/agent # scan a directory or specific files
ocr scan --resume <session-id> # resume an interrupted full-file scan
# Delegation mode — let your AI coding agent perform the review itself
# OCR handles file selection and rule resolution; no LLM configuration needed
ocr delegate preview
ocr delegate rule src/main.go src/handler.go
Documentation
Full documentation lives at open-codereview.ai/docs:
- Quickstart — install and run your first review
- Installation — all platforms and package managers
- CLI Reference — every command and flag
- Review Rules — customize review rules with path filtering and targeting
- Configuration — config keys and environment variables
- MCP Server — extend the review agent with external tools
- Coding Agent Integrations — choose the platform you use
- Claude Code — install a plugin with review slash commands
- Codex — install a plugin with callable review skills
- Cursor — install a plugin with portable review skills
- OpenCode — install native review tools and slash commands
- QCA Forward — run delegation mode with the QCA host model and a ready-to-publish template
- Skill-compatible agents — install the portable agent skill
- Review Execution Modes — after integration, choose which LLM performs the review
- Default (OCR-managed) — OCR runs the review using its configured LLM
- Delegation Mode — your coding agent runs the review using its own LLM; no OCR API key required
- CI/CD Integration — GitHub Actions, GitLab CI, GitFlic CI, and Gerrit integration
- Session Viewer — browse and replay review sessions in browser
- Telemetry — OpenTelemetry integration for observability
- FAQ — common questions and troubleshooting
Contributing
This project exists thanks to all the people who contribute. See CONTRIBUTING.md for development setup, coding guidelines, and how to submit pull requests.
License
Apache-2.0 — Copyright 2026 Alibaba
File tree
673alibaba/open-code-reviewView on GitHub
.claude/
.claude-plugin/
marketplace.json
commands/
commit.md
open-code-review.md
tag.md
.github/
dependabot.yml
ISSUE_TEMPLATE/
bug_report.yml
config.yml
docs_report.yml
feature_request.yml
pull_request_template.md
release.yml
workflows/
ci.yml
codeql.yml
deploy-pages.yml
ocr-review.yml
pages-ci.yml
release.yml
translation-sync.yml
vscode-ext.yml
.gitignore
.npmignore
action.yml
ASSURANCE_CASE.md
bin/
ocr.js
cmd/
opencodereview/
apply_provider_field_test.go
background_file_test.go
background_file.go
budget_output_test.go
compat_test.go
completion.go
config_cmd_test.go
config_cmd.go
config_dispatch_test.go
config_runset_test.go
config_unset_error_test.go
delegate_cmd.go
delegate_exec_test.go
delegate_helpers_test.go
emit_run_result_test.go
flag_suggest_test.go
flag_suggest.go
flags_test.go
git_test.go
git.go
llm_cmd.go
main.go
misc_helpers_test.go
output_helpers_test.go
output_manifest_test.go
output_test.go
output.go
parent_cmd_test.go
procattr_unix.go
procattr_windows.go
provider_cmd_test.go
provider_cmd.go
provider_config_apply_test.go
provider_tui_cpinput_test.go
provider_tui_customform_test.go
provider_tui_deleteconfirm_test.go
provider_tui_editsave_test.go
provider_tui_funcs_test.go
provider_tui_manualenter_test.go
provider_tui_modeltui_test.go
provider_tui_persist_test.go
provider_tui_rollback_test.go
provider_tui_savefail_test.go
provider_tui_test.go
provider_tui.go
review_cmd_test.go
review_cmd.go
review_helpers_test.go
review_mcp_more_test.go
review_resume_more_test.go
root.go
rules_check_test.go
rules_cmd.go
scan_cmd_test.go
scan_cmd.go
scan_helpers_test.go
scan_resume_more_test.go
session_cmd_test.go
session_cmd.go
session_complete_test.go
session_display_more_test.go
shared_flags.go
shared_llmruntime_test.go
shared_test.go
shared.go
shell_unix.go
shell_windows.go
smallfiles_test.go
version.go
viewer_cmd.go
zero_args_test.go
CODE_OF_CONDUCT.md
CONTRIBUTING.ja-JP.md
CONTRIBUTING.ko-KR.md
CONTRIBUTING.md
CONTRIBUTING.ru-RU.md
CONTRIBUTING.zh-CN.md
examples/
bitbucket_pipelines/
bitbucket-pipelines.yml
README.md
codeup_ci/
codeup-flow.yml
post_review_test.py
post_review.py
README.md
gerrit_ci/
Jenkinsfile
post_review_test.py
post_review.py
README.md
gitflic_ci/
gitflic-ci.yaml
post_review_test.py
post_review.py
README.md
github_actions/
ocr-review.yml
README.md
gitlab_ci/
.gitlab-ci.yml
post_review_test.py
post_review.py
README.md
README.md
extensions/
vscode/
__mocks__/
vscode.js
.eslintrc.json
.gitignore
.vscode/
launch.json
.vscodeignore
jest.config.js
LICENSE
package.json
package.nls.json
package.nls.zh-cn.json
prototype.html
README.md
README.zh-CN.md
resources/
icon.png
icon.svg
src/
extension/
commands.ts
extension.ts
providers/
__tests__/
commentAnchor.test.ts
lineOffset.test.ts
commentAnchor.ts
CommentProvider.ts
ConfigPanelProvider.ts
lineOffset.ts
SidebarProvider.ts
services/
__tests__/
cliParse.test.ts
CliService.cancel.test.ts
CliService.test.ts
configDraft.test.ts
configParse.test.ts
gitMap.test.ts
GitService.test.ts
ReviewSession.test.ts
shellEnv.test.ts
cliParse.ts
CliService.ts
configDraft.ts
configParse.ts
ConfigService.ts
gitMap.ts
GitService.ts
ReviewSession.ts
shellEnv.ts
shared/
configUtils.ts
constants.ts
i18n.ts
messages.ts
providers.ts
types.ts
webview/
__tests__/
store.test.ts
App.tsx
bridge.ts
components/
CommentCard.tsx
CustomProviderManager.tsx
EnvSetupGuide.tsx
FileList.tsx
LogViewer.tsx
PasswordInput.tsx
Select.tsx
configPanel.tsx
ConfigPanelApp.tsx
configStore.ts
I18nProvider.tsx
index.tsx
store.ts
styles/
global.css
views/
CancelledView.tsx
ConfigView.tsx
DoneView.tsx
EmptyView.tsx
FailedView.tsx
IdleView.tsx
RunningView.tsx
tsconfig.extension.json
tsconfig.json
tsconfig.webview.json
webpack.config.js
yarn.lock
go.mod
go.sum
GOVERNANCE.md
imgs/
benchmark-en.png
benchmark-ja.png
benchmark-ru.png
benchmark-zh.png
highlights-en.png
highlights-ja.png
highlights-ru.png
highlights-zh.png
logo-core.svg
logo.svg
providers.jpg
install.ps1
install.sh
internal/
agent/
agent_test.go
agent.go
budget_test.go
coverage_test.go
estimate_test.go
estimate.go
getters_test.go
init_test.go
manifest_hash_test.go
manifest_integration_test.go
preview_run_test.go
preview_test.go
preview.go
util_test.go
util.go
config/
allowlist/
allowed_ext_test.go
allowed_ext.go
default_exclude_patterns.json
supported_file_types.json
rules/
canonical_config_test.go
resolve_github_test.go
rule_docs/
arkts.md
astro.md
bicep.md
build_gradle.md
c.md
cargo_toml.md
composer_json.md
cpp.md
default.md
freemarker.md
github_config.md
github_workflows.md
go.md
graphql.md
haskell.md
java.md
json.md
julia.md
kotlin.md
mapper_dao_xml.md
nim.md
nix.md
package_json.md
php.md
po.md
pom_xml.md
pot.md
prisma.md
properties.md
protobuf.md
python.md
rust.md
terraform.md
ts_js_tsx_jsx.md
yaml.md
system_rules_test.go
system_rules_unmarshal_test.go
system_rules.go
system_rules.json
template/
prompts/
main_task_system.md
main_task_user.md
memory_compression_task_system.md
memory_compression_task_user.md
plan_task_system.md
plan_task_user.md
re_location_task_system.md
re_location_task_user.md
review_filter_task_system.md
review_filter_task_user.md
scan_template.json
task_template.json
template_test.go
template.go
testconnection/
task.json
testconnection_test.go
testconnection.go
toolsconfig/
tools.json
toolsconfig_test.go
toolsconfig.go
delegate/
format_test.go
format.go
rulegroup_test.go
rulegroup.go
diff/
first_line_test.go
git_resolve_test.go
git_test.go
git.go
gitignore_test.go
gitignore.go
hunk_test.go
hunk.go
parser_test.go
parser.go
relocation_test.go
relocation.go
resolver_test.go
resolver.go
workspace_file_test.go
workspace_file.go
gitcmd/
runner_test.go
runner.go
llm/
bpe_data/
cl100k_base.tiktoken
client_params_test.go
client_test.go
client.go
embedded_loader_test.go
embedded_loader.go
message_test.go
protocol_test.go
protocol.go
providers_test.go
providers.go
resolver_norm_test.go
resolver_shellrc_test.go
resolver_test.go
resolver.go
responses_client_test.go
responses_client.go
usage_resolver_test.go
usage_resolver.go
llmloop/
compression_test.go
compression.go
init_test.go
loop_execute_more_test.go
loop_execute_test.go
loop_test.go
loop.go
pool_test.go
pool.go
runner_test.go
mcp/
client_test.go
client.go
provider_test.go
... 392 moreMore Flows by @alibaba.
@alibabaFAQ
alibaba-open-code-review is a Claude Code plugin with 4 hand-picked skills for development work, indexed on Flowy. Install it with the command on its page. It includes open-code-review-delegate, open-code-review, open-code-review-delegate. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
- What is alibaba-open-code-review?
- 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.
- How do I install alibaba-open-code-review?
- Run these in Claude Code: /plugin marketplace add alibaba/open-code-review then /plugin install open-code-review@open-code-review. Then prompt normally.
- Does alibaba-open-code-review auto-invoke its skills?
- Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
- Is alibaba-open-code-review free?
- Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.