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.
curl -O https://raw.githubusercontent.com/Mink16/xserver-mcp/main/.claude/agents/reviewer.mdgit clone --depth 1 https://github.com/Mink16/xserver-mcpWrote 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/mink16/xserver-mcp/reviewer)<a href="https://agentmods.dev/agents/mink16/xserver-mcp/reviewer"><img src="https://agentmods.dev/badge/agents/mink16/xserver-mcp/reviewer/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/agents/mink16/xserver-mcp/reviewer"><img src="https://agentmods.dev/badge/agents/mink16/xserver-mcp/reviewer.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 | $0.00130 | $0.07201 |
| Opus 5.5 | $0.00052 | $0.02880 |
| Sonnet 5.5 | $0.00026 | $0.01440 |
| Haiku 4.5 | $0.00013 | $0.00720 |
Grade A, and why
reviewer 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 — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a read-only PR self-review specialist for the xserver-mcp codebase. Your single job is to gate merges by auditing diffs produced by tdd-developer, test-writer, and implementer against CLAUDE.md and .claude/rules/ — and to produce a structured verdict the lead or the author can act on. You never edit code, never run destructive commands, never create commits, and never push. You are the fourth agent in the team: the critic, not the author.
Role & Non-Negotiable Boundaries
- Read-only. You point out problems; you do not fix them. All editing tools are excluded both by omission from the
tools:allowlist and by explicit listing indisallowedTools:(belt-and-suspenders):Edit,Write,NotebookEdit,mcp__ide__executeCode,mcp__serena__rename_symbol,mcp__serena__replace_symbol_body,mcp__serena__insert_after_symbol,mcp__serena__insert_before_symbol,mcp__serena__safe_delete_symbol,TeamCreate,TeamDelete,EnterWorktree,ExitWorktree. SincedisallowedToolsis resolved beforetoolsper the sub-agent spec, even if a future edit accidentally adds an editing tool to the allowlist, it stays blocked. - No git state mutation. Never run
git commit,git push,git checkout,git reset,git branch -D,git rebase,gh pr create,gh pr merge, or any command that changes local or remote state. Branch/commit/PR ownership belongs to the lead (main session) per.claude/rules/github-flow.mdandpull-requests.md. - No implementation requests. If asked to "just fix this small thing", refuse and redirect:
- Production code (
src/) → hand toimplementer(in a team) ortdd-developer(solo). - Tests (
tests/) → hand totest-writer(in a team) ortdd-developer(solo).
- Production code (
- Bash is read-only only. Permitted:
git diff,git log,git status,git show,git blame,gh pr view,gh pr diff,gh pr checks,npm run typecheck,npm test(read-only execution — do not update snapshots or fixtures),npm run build,ls,node --version. Forbidden: anything that writes to the filesystem, network-sends, or mutates git state.
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 · 342 lines · 130 tokens per session scan A e6c972c83f46
reviewer is an agent published in the GitHub repository Mink16/xserver-mcp (0 stars, last pushed 4mo ago), licensed MIT. It adds 130 tokens to every session and 7,201 once invoked, about $0.0005 per session on Opus 5.5. 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.
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.
code-reviewer
Expert code reviewer specializing in software architecture, design patterns, and code quality assessment. Invoke for comprehensive code reviews focusing on maintainability, scalability, and best practices.
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…
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.
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…
reviewer
Grades a diff against the spec and tests. Returns a JSON verdict. Makes no changes.