Agent Skill
Open Code Review Delegate skill
open-code-review-delegatealibaba/open-code-reviewplugins/open-code-review/skills/open-code-review-delegate/SKILL.md
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.
always on
68 tokname + description
once used
2,005 tokSKILL.md body
bundled files
0
repo stars
48kGitHub
Install the Open Code Review Delegate skill
Skills CLI (Claude Code, Codex, Cursor and others)
npx skills add https://github.com/alibaba/open-code-review --skill open-code-review-delegate
Claude Code, by hand (all projects)
git clone --depth 1 https://github.com/alibaba/open-code-review.git /tmp/open-code-review mkdir -p ~/.claude/skills cp -R /tmp/open-code-review/plugins/open-code-review/skills/open-code-review-delegate ~/.claude/skills/open-code-review-delegate
For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.
What it costs your context
Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.
| When | What loads | Cost |
|---|---|---|
| Every session | Name and description | 68 tok |
| When the agent uses it | The SKILL.md instructions | 2,005 tok |
| Only if opened | No bundled files | — |
Until it is used, open-code-review-delegate costs about 20× less than the median MCP server we measured (1,362 tokens on every turn). Installing all 4 skills from alibaba/open-code-review would load 330 tokens of descriptions. Skills vs MCP study
Checks
Our checks found nothing to flag: it follows the Agent Skills specification's naming and size guidelines and doesn't pipe downloads into a shell.
Checked 2026-10-22 · method
What's inside
The headings of its SKILL.md. Read the full file on GitHub.
- Open Code Review — Delegation Mode
- Workflow
- Step 1: Preview — Determine What to Review
- Step 2: Get Rules for Files
- Step 3: Get Diffs
- Step 4: Review Each File
- Step 5: Format Output
- Step 6: Classify and Report
- Step 7: Fix (Optional)
- Sub-commands Reference
- Shared Flags
- Gotchas
- Recovering Oversized Background Context
- Troubleshooting CLI Version Compatibility
More skills from alibaba/open-code-review
- open-code-reviewalibaba/open-code-review
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.
48k97 tok idle · 2,810 in use - open-code-reviewalibaba/open-code-review
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.
48k97 tok idle · 2,760 in use - open-code-review-delegatealibaba/open-code-review
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.
48k68 tok idle · 1,951 in use