agentmods.dev

xserver-mcp: Agent for Claude Code

.claude/agents/reviewer-architect.md

reviewer-architect is an agent for Claude Code from Mink16/xserver-mcp. It costs 113 tokens per session (5,797 once invoked), scanned A, original, MIT.

A set of instructions for creating a read-only code-review helper for the xserver-mcp project, which connects AI tools to a server-panel API. It adds a project-specific reviewer to a test-driven development (TDD) team.

In plain words
What is it for?
It is for designing the reviewer agent, checking work from the TDD development and testing agents, and coordinating review results between agents.
Why use it?
It helps catch project rules and integration issues after other coding agents finish, without changing the code or duplicating standard review commands.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

This is Mink16/xserver-mcp's own configuration. It tells Claude Code how to work on xserver-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything xserver-mcp configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/mink/work/xserver-mcp/.claude/agent-memory/reviewer/.

not rated 0repo 2mo ago A scan 113 tokens original MIT
View source ↗ Mink16/xserver-mcp
Reuse

Borrowing it

Nothing to install: this file belongs to Mink16/xserver-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Mink16/xserver-mcp/main/.claude/agents/reviewer-architect.md
Clone the repo
git clone --depth 1 https://github.com/Mink16/xserver-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for reviewer-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/mink16/xserver-mcp/reviewer-architect/github.svg)](https://agentmods.dev/agents/mink16/xserver-mcp/reviewer-architect)
Your own site
<a href="https://agentmods.dev/agents/mink16/xserver-mcp/reviewer-architect"><img src="https://agentmods.dev/badge/agents/mink16/xserver-mcp/reviewer-architect/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.

agentmods 80×15 button for reviewer-architect

Your own site · 80×15
<a href="https://agentmods.dev/agents/mink16/xserver-mcp/reviewer-architect"><img src="https://agentmods.dev/badge/agents/mink16/xserver-mcp/reviewer-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 113 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,797 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00113 $0.05797
Opus 5 $0.00056 $0.02899
Sonnet 5 $0.00023 $0.01159
Haiku 4.5 $0.00011 $0.00580

Measured 8d ago against content hash a35b22d16fa3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

reviewer-architect 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 8d 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.

.claude/agents/reviewer-architect.md · 283 lines

How it starts

The opening of the file, as written. The whole thing — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an elite AI agent architect specializing in the xserver-mcp project (an MCP server wrapping the Xserver server-panel REST API). Your singular mission is to design and author .claude/agents/reviewer.md — a read-only, PR-self-review subagent that serves as the fourth member of this project's TDD agent roster, gating the output of tdd-developer, test-writer, and implementer.

Your operational constraints (non-negotiable)

  • You MUST NOT modify CLAUDE.md, docs/xserver-openapi.json, or any existing agent definition (tdd-developer.md, test-writer.md, implementer.md).
  • You MUST NOT edit .claude/rules/tdd-workflow.md without explicit user approval — you may only propose the table addition at the end.
  • You MUST produce a reviewer definition that does not duplicate what /review or /security-review slash commands already provide. The differentiator is xserver-mcp-specific rule enforcement and Agent Team SendMessage interop.
  • Output language is Japanese (primary); code identifiers and API names stay in the original.

Mandatory pre-work: read these files before writing anything

Read every file below (parallelize where possible) and internalize the structure/vocabulary before drafting:

  1. CLAUDE.md — Xserver API quirks, error normalization, IDN handling, rate limits
  2. .claude/rules/tdd-workflow.md — agent role matrix, Agent Team mode
  3. .claude/rules/github-flow.md
  4. .claude/rules/commit-messages.md
  5. .claude/rules/pull-requests.md — this is the canonical review checklist source
  6. .claude/agents/tdd-developer.md
  7. .claude/agents/test-writer.md
  8. .claude/agents/implementer.md — mirror frontmatter shape, heading hierarchy, and memory section exactly
  9. src/tools/helpers.ts — confirm runApi / mapErrorToNormalizedResult signatures
  10. src/client/errors.ts — confirm STATUS_TO_CODE map and error class hierarchy
  11. src/tools/domain.ts — confirm toPunycodeDomain / normalizeMailAddress / encodeMailAccount signatures
  12. src/tools/registry.ts — confirm toolsetNames and builders structure
  13. docs/xserver-openapi.json — read-only reference; DO NOT modify

Read the full file on GitHub · 283 lines

Changes

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.

  1. 8d ago First seen · 283 lines · 113 tokens per session scan A a35b22d16fa3

Subscribe to this mod's changes

reviewer-architect is an agent published in the GitHub repository Mink16/xserver-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 113 tokens to every session and 5,797 once invoked, about $0.0006 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 2026-08-31.

Code reviewdnsmailmcpmodel-context-protocolxserver
Related

Other agents, from other repositories

mcp-pr-reviewer

Autonomous PR reviewer for MCP server updates and additions. Reviews PRs that modify server.json files in the registry, determines compliance, and approves/merges safe changes. Use when processing MCP server PRs in bulk or reviewing individual PRs.

stacklok/toolhive-catalog · 55 tokens

devils-advocate

Adversarial reviewer that systematically attacks specs, implementations, and plans to find logical gaps, missed edge cases, implicit assumptions, and over/under-engineering. Maintains a playbook of attack patterns that evolves based on what actually finds bugs. Use on any artifact you want stress-tested before…

Kastalien-Research/thoughtbox · 66 tokens

verification-judge

Independently validate completed work against specifications and acceptance criteria. Use after work is marked complete to verify it actually meets requirements. This agent is deliberately isolated from producing agents — it validates outputs against specs, not intentions.

Kastalien-Research/thoughtbox · 47 tokens

triage-fix

Diagnose and repair technical failures in the codebase, build system, and integrations. Use when something breaks — test failures, build errors, integration breakdowns, runtime exceptions. This agent implements fixes autonomously within scope boundaries.

Kastalien-Research/thoughtbox · 50 tokens

silent-failure-hunter

Specialized adversarial agent for finding code paths that fail without producing visible errors. Targets hooks, state file pipelines, scheduled tasks, and error handlers. Particularly dangerous failures are those that produce plausible-looking wrong data rather than errors. Shares the adversarial playbook with…

Kastalien-Research/thoughtbox · 64 tokens

reviewer

Grades a diff against the spec and tests. Returns a JSON verdict. Makes no changes.

DanielHashmi/Q4_learning · 21 tokens