Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/alibaba/open-code-review/reviewgit clone --depth 1 https://github.com/alibaba/open-code-reviewWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00017 | $0.00371 |
| Opus 5 | $0.00009 | $0.00186 |
| Sonnet 5 | $0.00003 | $0.00074 |
| Haiku 4.5 | $0.00002 | $0.00037 |
Grade A, and why
review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
94% identical to open-code-review — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Invoke the professional code review Agent CLI tool OpenCodeReview (OCR) to review current code changes, and let the Agent autonomously decide whether to apply fixes.
Workflow
Step 1: Run Code Review
Run the OCR command:
ocr review --audience agent [user-args]
- Default (no user arguments): reviews staged, unstaged, and untracked changes (workspace mode).
- If the user provides
--commitor--c: pass through as-is. - If the user provides
--fromand--to: pass through as-is. - (Optional) Provide
--background "requirement context"to review whether the requirements are correctly implemented. - (Optional) Provide
--background-file ./requirements.mdto load the same context from a Markdown file (sanitised and limited to 8000 characters). Takes precedence over--backgroundwhen both are set. - Capture full stdout. Set a 5-minute timeout.
- If the
ocrcommand is not found, install it by runningnpm i -g @alibaba-group/open-code-review.
Step 2: Filter and Evaluate
For each comment, assess its validity and quality:
- High: Obvious bugs, security issues, clear mistakes, or well-founded suggestions with precise fix proposals
- Medium: Reasonable concerns but context-dependent, style/performance suggestions, or fixes that require manual implementation
- Low: Likely false positives, lacking sufficient context, nitpicks, or meaningless suggestions
Silently discard low-confidence comments. Display the remaining comments.
Step 3: Fix
Automatically fix issues and suggestions that are worth adopting.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 37 lines · 17 tokens per session scan A 24802dc9ed2f
review is a command published in the GitHub repository alibaba/open-code-review (21,659 stars, last pushed 4d ago), licensed Apache-2.0. It adds 17 tokens to every session and 371 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to open-code-review, differing in 4 lines, and is treated as a copy.
Other commands, from other repositories
full-review
Run a full review — code, architecture, browser, and UX. User input: $ARGUMENTS.
commit
Commit current changes. User input: $ARGUMENTS.
harness
Run the full Auto-Harness orchestration flow. /auto-harness:harness.
qa-parallel
Advance parallel Evaluator-side actions only. Auto-selects review, QA, retest, or final report from status.md. /auto-harness:qa-parallel [sprint].
build-parallel
Advance parallel Generator-side actions only. Auto-selects contract, build, or fix from status.md. /auto-harness:build-parallel [sprint].
plan
Run the Planner side only. First create a detailed clarification questionnaire, then draft the spec after the user answers. /auto-harness:plan.