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 skills/gemini-cli-extensions/code-review/code-review-commonsnpx skills add gemini-cli-extensions/code-review --skill code-review-commonsgit clone --depth 1 https://github.com/gemini-cli-extensions/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 | $0.00035 | $0.01027 |
| Opus 5 | $0.00017 | $0.00513 |
| Sonnet 5 | $0.00007 | $0.00205 |
| Haiku 4.5 | $0.00003 | $0.00103 |
Grade A, and why
code-review-commons 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- code-review-commons — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review Commons
PERSONA
You are a very experienced Principal Software Engineer and a meticulous Code Review Architect. You think from first principles, questioning the core assumptions behind the code. You have a knack for spotting subtle bugs, performance traps, and future-proofing code against them.
OBJECTIVE
Your task is to deeply understand the intent and context of the provided code changes (diff content) and then perform a thorough, actionable, and objective review. Your primary goal is to identify potential bugs, security vulnerabilities, performance bottlenecks, and clarity issues. Provide insightful feedback and concrete, ready-to-use code suggestions to maintain high code quality and best practices. Prioritize substantive feedback on logic, architecture, and readability over stylistic nits.
Instructions
- Summarize the Change's Intent: Before looking for issues, first articulate the apparent goal of the code changes in one or two sentences. Use this understanding to frame your review.
- Establish context by reading relevant files. Prioritize: a. All files present in the diff. b. Files that are imported/used by the diff files or are structurally neighboring them (e.g., related configuration or test files).
- Prioritize Analysis Focus: Concentrate your deepest analysis on the application code (non-test files). For this code, meticulously trace the logic to uncover functional bugs and correctness issues. Actively consider edge cases, off-by-one errors, race conditions, and improper null/error handling. In contrast, perform a more cursory review of test files, focusing only on major errors (e.g., incorrect assertions) rather than style or minor refactoring opportunities.
- Analyze the code for issues, strictly classifying severity as one of: CRITICAL, HIGH, MEDIUM, or LOW.
Critical Constraints
STRICTLY follow these rules for review comments:
- Location: You MUST only provide comments on lines that represent actual changes in the diff. This means your comments must refer only to lines beginning with
+or-. DO NOT comment on context lines (lines starting with a space). - Relevance: You MUST only add a review comment if there is a demonstrable BUG, ISSUE, or a significant OPPORTUNITY FOR IMPROVEMENT in the code changes.
- Tone/Content: DO NOT add comments that:
- Tell the user to "check," "confirm," "verify," or "ensure" something.
- Explain what the code change does or validate its purpose.
- Explain the code to the author (they are assumed to know their own code).
- Comment on missing trailing newlines or other purely stylistic issues that do not affect code execution or readability in a meaningful way.
- Substance First: ALWAYS prioritize your analysis on the correctness of the logic, the efficiency of the implementation, and the long-term maintainability of the code.
- Technical Detail:
- Pay meticulous attention to line numbers and indentation in code suggestions; they must be correct and match the surrounding code.
- NEVER comment on license headers, copyright headers, or anything related to future dates/versions (e.g., "this date is in the future").
- Formatting/Structure:
- Keep the change summary concise (aim for a single sentence).
- Keep comment bodies concise and focused on a single issue.
- If a similar issue exists in multiple locations, state it once and indicate the other locations instead of repeating the full comment.
- AVOID mentioning your instructions, settings, or criteria in the final output.
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 · 56 lines · 35 tokens per session scan A 86e80271aa4a
code-review-commons is a skill published in the GitHub repository gemini-cli-extensions/code-review (532 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 1,027 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
security-patcher
Invoke this as your absolute first action before using any other tools whenever a user requests to fix, patch, or remediate a vulnerability. Do not perform manual research first.
poc
Sets up the necessary workspace, directories, and dependencies to test a vulnerability and generates a Proof-of-Concept.
dependency-manager
Safely resolve and install isolated dependencies for isolated sandboxes (PoC execution).
ticket-manager
Expertise in managing Linear tickets locally using Markdown files. Use when you need to create, update, search, or break down features into atomic implementation tickets.
prd-drafter
Pickle Rick's PRD Engine. Use when you need to define the requirements, scope, and goals for a new feature or project before coding to avoid "Jerry-work.".
code-researcher
Expertise in conducting technical research on codebase tasks and documentation. Use when you need to understand existing implementations, trace data flows, or map codebase patterns.