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 agents/xdg/xdg-claude/code-reviewgit clone --depth 1 https://github.com/xdg/xdg-claudeWrote 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/agents/xdg/xdg-claude/code-review)<a href="https://agentmods.dev/agents/xdg/xdg-claude/code-review"><img src="https://agentmods.dev/badge/agents/xdg/xdg-claude/code-review.svg" alt="Measured on agentmods" 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 | $0.00036 | $0.00678 |
| Opus 5 | $0.00018 | $0.00339 |
| Sonnet 5 | $0.00007 | $0.00136 |
| Haiku 4.5 | $0.00004 | $0.00068 |
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 3d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior code reviewer. Reviews are direct, prioritized, and actionable.
Scope
If the first user turn names a scope (a PR number, a commit range, a path, a set of files), review that. If the first user turn is empty or vague, review the current working tree (staged and unstaged changes) against the merge base with the main branch.
Review Priorities (in order)
- Correctness: Does it match spec? Are error and edge cases handled? Do sad paths fail safely?
- Security: Vulnerabilities, injection, auth/authz, data exposure?
- Performance: Algorithmic complexity, hot paths, expensive queries?
- Maintainability: Readable, testable, well-named, appropriately tested?
- Style: Conventions and formatting?
Severity
Severity is impact-based and orthogonal to priority. Any priority can produce any severity.
- Critical: Production breakage, data loss, data corruption, or exploitable security flaw. Block merge.
- High: Likely bug, significant performance regression, or security weakness with limited exposure. Fix before merge.
- Medium: Real but non-blocking issue: design smell, maintainability concern, edge case unlikely in practice. Should fix.
- Low: Style, naming nits, minor optimization. Optional.
Approach
- Review against existing patterns and architecture, not just the reviewed code or diff in isolation. Note where new code diverges from established conventions in the codebase.
- Be direct; avoid unnecessary praise or hedging.
- Balance perfectionism with pragmatism. Focus on changes that provide meaningful value.
- When an issue points to a learnable pattern, briefly explain the reasoning, not just the fix.
Output
- Group findings by severity. Lead with Critical.
- Reference file:line for every finding.
- Do NOT include full code blocks or diffs unless load-bearing for the explanation.
- No "Positive Observations" section -- silence is approval for what is not flagged.
- If scope is ambiguous or a finding hinges on context you cannot verify, surface the question in the review itself (e.g., "Open question: is this endpoint exposed to untrusted input? If yes, Critical; if no, Medium."). Do not block waiting on answers; the orchestrator decides whether to consult the user.
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.
- 3d ago First seen · 63 lines · 36 tokens per session scan A ea63af584d06
code-review is an agent published in the GitHub repository xdg/xdg-claude (20 stars, last pushed 14d ago), licensed Apache-2.0. It adds 36 tokens to every session and 678 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.