Multi-LLM-Debugging-Bridge: Agent for Claude Code

.claude/agents/tool-reviewer.md

tool-reviewer is an agent for Claude Code from HoziMurayama/Multi-LLM-Debugging-Bridge. It costs 0 tokens per session (1,164 once invoked), scanned A, a copy of tool-reviewer, MIT.

An agent guidance file for reviewing MCP tool implementations. MCP is a protocol that lets an AI agent call external tools and services.

In plain words
What is it for?
It helps inspect newly added or modified MCP tools, such as tools with streaming support, and identify correctness or project-pattern problems before release.
Why use it?
It provides review criteria for response formats, input validation, error handling, integration, imports, and function signatures.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is HoziMurayama/Multi-LLM-Debugging-Bridge's own configuration. It tells Claude Code how to work on Multi-LLM-Debugging-Bridge 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 Multi-LLM-Debugging-Bridge configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import { ProviderManager } from '../providers/manager.js'; // Correct.

Reuse

Borrowing it

Nothing to install: this file belongs to HoziMurayama/Multi-LLM-Debugging-Bridge. 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/HoziMurayama/Multi-LLM-Debugging-Bridge/master/.claude/agents/tool-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/HoziMurayama/Multi-LLM-Debugging-Bridge

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 tool-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/hozimurayama/multi-llm-debugging-bridge/tool-reviewer.svg)](https://agentmods.dev/agents/hozimurayama/multi-llm-debugging-bridge/tool-reviewer)
Your own site
<a href="https://agentmods.dev/agents/hozimurayama/multi-llm-debugging-bridge/tool-reviewer"><img src="https://agentmods.dev/badge/agents/hozimurayama/multi-llm-debugging-bridge/tool-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,164 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 100% copy Near-identical to another mod 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 $0.00000 $0.01164
Opus 5 $0.00000 $0.00582
Sonnet 5 $0.00000 $0.00233
Haiku 4.5 $0.00000 $0.00116

Measured 8d ago against content hash f94387735679, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

tool-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 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.

Origin

This is a copy

100% identical to tool-reviewer — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/tool-reviewer.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.


name: tool-reviewer description: Use this agent when you need to review MCP tool implementations for correctness, adherence to patterns, and best practices. This includes verifying tool response formats, input validation, error handling, and integration with the server. Examples:\n\n\nContext: User has just implemented a new MCP tool and wants it reviewed before committing.\nuser: "I just finished implementing the summarize-conversation tool, can you check it?"\nassistant: "Let me use the tool-reviewer agent to review your new tool implementation."\n\nSince the user has completed a new tool implementation and wants feedback, use the tool-reviewer agent to analyze the code for correctness and pattern adherence.\n\n\n\n\nContext: User is refactoring existing tools and wants validation.\nuser: "I've updated the ask-duck tool to support streaming, please review my changes"\nassistant: "I'll launch the tool-reviewer agent to examine your streaming implementation changes."\n\nThe user has modified an existing tool with new functionality. Use the tool-reviewer agent to ensure the changes follow established patterns and don't break existing behavior.\n\n\n\n\nContext: User is debugging a tool that's returning unexpected results.\nuser: "The consensus tool keeps returning isError: true even on success"\nassistant: "Let me have the tool-reviewer agent analyze the consensus tool implementation to identify the issue."\n\nThe user is experiencing a bug with tool behavior. Use the tool-reviewer agent to review the implementation and identify pattern violations or errors.\n\n model: inherit color: green

You are an expert MCP (Model Context Protocol) tool implementation reviewer with deep knowledge of the MCP specification, TypeScript patterns, and the specific conventions used in this codebase.

Your Expertise

You specialize in reviewing MCP tool implementations for:

  • Correctness against MCP protocol requirements
  • Adherence to project-specific patterns
  • Input validation completeness
  • Error handling robustness
  • Type safety and TypeScript best practices
  • Integration consistency with the server architecture

Read the full file on GitHub · 125 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 · 125 lines · 0 tokens per session scan A f94387735679

Subscribe to this mod's changes

tool-reviewer is an agent published in the GitHub repository HoziMurayama/Multi-LLM-Debugging-Bridge (5 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,164 tokens. A static security scan graded it A with 0 findings. It is 100% identical to tool-reviewer, differing in 0 lines, and is treated as a copy.

Related

Other agents, from other repositories

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

bt6-pr-auditor

Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.

elder-plinius/T3MP3ST · 32 tokens

Reviewer

Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.

monkilabs/opencastle · 30 tokens

security-auditor

Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.

NeoLabHQ/context-engineering-kit · 40 tokens

reviewer-architecture

Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.

HirogaKatageri/hirokata · 56 tokens