Index of every page on this site: llms.txt
All skills
alibaba avatar

/open-code-review-delegate

@d29ca20
by alibabaalibaba/open-code-review55k stars
4,532
Run it yourself

Review workspace changes, PRs, commits, or branch comparisons with the host agent's model. OCR's CLI handles file selection and rule resolution; this skill defines the review workflow, coverage requirements, and output format. Use when the user has no separate API key for OCR or wants to reuse their coding-agent subscription or model setup. For OCR's full native pipeline with its own model provider, choose open-code-review instead.

Use this Skill: https://skilld.dev/gh/alibaba/open-code-review/open-code-review-delegate

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈116 tokens for metadata: the name and description. ≈2.3k when used: this file.

Description uses 5.8% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈463 characters, or 5.8%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Open Code Review — Delegation Mode

Workflow

Step 1: Preview — Determine What to Review

Skip OCR provider setup and ocr llm test; the host agent's authentication, usage limits, and costs still apply.

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

With --from and no --to, both delegate subcommands default to HEAD. Range review compares the merge-base to the target commit and excludes staged, unstaged, and untracked changes. Omit range/commit flags for workspace mode; range and commit flags are mutually exclusive.

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
Current branch against main ocr delegate preview --from main
Single commit ocr delegate preview -c abc123

Step 2: Get Rules for Files

ocr delegate rule --format json [--from <ref> [--to <ref>]] [--commit <hash>] <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.

Pass the same range or commit flags as in Step 1 so rules are resolved against the same target. For example, pair ocr delegate preview --from main with ocr delegate rule --from main --format json <path...>.

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

Identify the review mode as delegation.

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
  • Medium: Performance concerns, error handling gaps, maintainability issues — report with context
  • Low: Style nits, minor suggestions — report only if clearly valuable

Discard likely false positives silently.

Step 7: Fix (Optional)

If the user requested "review and fix":

  • Apply High/Critical fixes directly
  • Describe Medium fixes that require manual intervention
  • Skip Low-priority items unless trivial

Sub-commands Reference

Command Purpose
ocr delegate preview Which files to review + mode/ref metadata
ocr delegate rule <path...> Review rules grouped by content

Shared Flags

Flag Description
--from <ref> Source ref for range mode
--to <ref> Target ref for range mode; defaults to HEAD when --from is supplied in either subcommand
-c, --commit <hash> Single commit mode
--repo <path> Repository root (default: cwd)
--rule <path> Custom rule.json path
--exclude <patterns> Comma-separated exclude patterns
-b, --background <text> Business context
-B, --background-file <path> Business context from Markdown file (takes precedence over -b)
-f, --format <text|json> Output format; use json for agent integrations

Gotchas

  • Host-driven analysis — OCR's native review agent, positioning, and reflection modules do not run in delegation mode.
  • Rules are grouped — Files sharing the same rule are grouped together in the output. You can pass any number of paths per call; for large changes, fetch rules per-batch as you review.
  • Working directory matters — ocr delegate operates on the Git repo at the current directory. Use --repo /path to override.
  • Untracked files in workspace mode — preview includes untracked files. For these, read the file directly instead of using git diff.
  • Background context — pass --background to preview when you have requirement context; it appears in the output for your reference during review.
  • Coverage is mandatory — every reviewable_files entry must end as reviewed or explicitly skipped; do not silently omit files.

Recovering Oversized Background Context

--background-file has two independent limits. The raw file must not exceed 1 MiB, and the sanitized content must not exceed 8000 characters. Either condition aborts the command. When the command reports either limit:

  1. Do not silently truncate the source file.
  2. Summarize the original material while preserving its requirements, constraints, acceptance criteria, and other review-critical details.
  3. Retry the affected command by passing the summary as one shell-safe argument (for example, use a quoted/escaped argument produced by the host shell, or write it to a new size-bounded file and pass that file). Do not place untrusted summary text directly in a double-quoted shell template; $(), backticks, quotes, and variable references can still be evaluated. Omit the original --background-file so the CLI does not reload the same oversized file and fail again.
  4. If a faithful summary is not possible, omit the OCR background entirely and read the original material directly during the review.

Troubleshooting CLI Version Compatibility

If an OCR command fails with command not found, install the CLI with npm install -g @alibaba-group/open-code-review if your environment permits, then retry the same command. If installation is not permitted, explain the prerequisite and stop; do not substitute ocr review or ask for an API key.

The --format flag is available in ocr v1.9.0 and later. The Skill and the installed CLI can be updated independently. If a requested preview or rule command with --format json fails specifically with unknown flag: --format, rerun it without the flag and use text output for the rest of the delegation run. Preserve the explicit mode, ref, file, and rule information from that output; do not parse text output as JSON or invent missing schema fields. Do not retry without the flag for any other error; report it and stop the affected workflow.

The host-agent Skill may consume the equivalent text output to complete its review checklist. Programmatic integrations that require schema_version or other JSON fields must require a JSON-capable CLI instead: verify with ocr --version and upgrade when necessary:

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

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 warningtoday3 checks · Risk SAFE
  • Gen Agent Trust Hubtoday

    The skill is a code review utility that uses the 'ocr' CLI and Git to analyze changes in a repository. It is primarily safe but carries a low risk of indirect prompt injection as it processes external code content which could contain malicious instructions designed to bias the AI's review.

  • Socket4d

    No alerts

  • Snyktoday

    Risk: MEDIUM · 1 issue

Signed by skilld at d29ca20. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 5 days ago
Other metadata
compatibility
Requires the `ocr` CLI installed (via `npm install -g @alibaba-group/open-code-review` or GitHub release binary). Does NOT require a configured LLM endpoint — delegation mode is LLM-free on the OCR side.
metadata
{
  "author": "alibaba",
  "homepage": "https://github.com/alibaba/open-code-review",
  "version": "1.0.0"
}

README badge

README badge for alibaba/open-code-review/open-code-review-delegate