Borrowing it
Nothing to install: this file belongs to abdullah1854/MCPGateway. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/abdullah1854/MCPGateway/main/.agents/skills/code-review/SKILL.mdgit clone --depth 1 https://github.com/abdullah1854/MCPGatewayWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/abdullah1854/mcpgateway/code-review)<a href="https://agentmods.dev/skills/abdullah1854/mcpgateway/code-review"><img src="https://agentmods.dev/badge/skills/abdullah1854/mcpgateway/code-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/abdullah1854/mcpgateway/code-review"><img src="https://agentmods.dev/badge/skills/abdullah1854/mcpgateway/code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00000 | $0.01748 |
| Opus 5.5 | $0.00000 | $0.00699 |
| Sonnet 5.5 | $0.00000 | $0.00350 |
| Haiku 4.5 | $0.00000 | $0.00175 |
Grade A, and why
code-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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
code-review
Comprehensive code review for pull requests using parallel agents. Reviews for CLAUDE.md compliance, bugs, historical context, previous PR comments, and code comment guidance.
Metadata
- Version: 2.0.0
- Category: code-quality
- Source: anthropic-official
- License: MIT
Tags
code-review, pr-review, security, bugs, claude-md, agents
MCP Dependencies
- GitHub CLI (
gh) for PR interaction
Inputs
pr_number(string) (optional): Pull request number to reviewconfidence_threshold(number) (optional): Minimum confidence to report (default: 80)
Review Process
Phase 1: Eligibility Check (Haiku Agent)
Check if the PR:
- Is closed
- Is a draft
- Doesn't need review (automated or very simple)
- Already has a code review from earlier
If any condition is true, do not proceed.
Phase 2: CLAUDE.md Discovery (Haiku Agent)
Find all relevant CLAUDE.md files:
- Root CLAUDE.md (if exists)
- CLAUDE.md files in directories whose files the PR modified
Phase 3: PR Summary (Haiku Agent)
View the pull request and return a summary of the change.
Phase 4: Parallel Review (5 Sonnet Agents)
Launch 5 agents in parallel to independently code review:
| Agent | Focus Area |
|---|---|
| #1 | CLAUDE.md compliance audit |
| #2 | Shallow bug scan (focus on changes, avoid false positives) |
| #3 | Git blame and history context for bugs |
| #4 | Previous PRs and comments that may apply |
| #5 | Code comments compliance in modified files |
Each agent returns a list of issues with reasons (CLAUDE.md adherence, bug, historical context, etc.)
Phase 5: Confidence Scoring (Parallel Haiku Agents)
For each issue found, launch a Haiku agent to score confidence:
| Score | Meaning |
|---|---|
| 0 | Not confident - false positive or pre-existing issue |
| 25 | Somewhat confident - might be real, couldn't verify |
| 50 | Moderately confident - real but minor/nitpick |
| 75 | Highly confident - verified real issue, important |
| 100 | Absolutely certain - confirmed, will happen frequently |
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 276 lines · 0 tokens per session scan A b649e1242d1c
code-review is a skill published in the GitHub repository abdullah1854/MCPGateway (17 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,748 tokens. 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
github-commenting
How to post clean, rich, deduplicated GitHub PR review comments — suggestion blocks, multi-line anchors, markers, formatting rules. Load before posting or fixing any PR comment.
code-review
Review ServiceNow server-side scripts for ES5 violations, ACL/injection/XSS issues, N+1 queries, missing setLimit/error handling, hard-coded sysids, and business-rule recursion risks.
repo-conventions
NeuroLink's review standards — the critical rules to enforce, what NOT to comment on, the security bar, hot paths. Load before reviewing any change in this repository.
gh-address-comments
This skill should be used when addressing GitHub pull request review comments systematically with mandatory resolution tracking. Use when user says "address PR comments", "fix review feedback", "handle PR review", "resolve PR threads", or needs to ensure all review comments are addressed before merging. Fetches…
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.
deep-review
Parallel competency-based code review. Launches independent Agent reviewers per competency (security, performance, architecture, database, concurrency, error-handling, frontend, testing), each with a focused checklist and isolated context. Synthesizes findings into unified report with FIX/DEFER/ACCEPT triage. Use…