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

.claude/skills/tool-review/SKILL.md

tool-review is a skill for Claude Code from HoziMurayama/Multi-LLM-Debugging-Bridge. It costs 26 tokens per session (395 once invoked), scanned A, a copy of tool-review, MIT.

A review checklist for an MCP tool implementation. MCP is a standard interface that lets an AI coding tool call functions provided by another program.

In plain words
What is it for?
Use it after creating or changing a tool to inspect its source code, server registration, input schema, dependencies, and error responses.
Why use it?
It helps catch missing validation, incorrect registration, weak error handling, unsafe input handling, and differences from the project’s existing code patterns.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md.

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 →

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/skills/tool-review/SKILL.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-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/hozimurayama/multi-llm-debugging-bridge/tool-review/github.svg)](https://agentmods.dev/skills/hozimurayama/multi-llm-debugging-bridge/tool-review)
Your own site
<a href="https://agentmods.dev/skills/hozimurayama/multi-llm-debugging-bridge/tool-review"><img src="https://agentmods.dev/badge/skills/hozimurayama/multi-llm-debugging-bridge/tool-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.

agentmods 80×15 button for tool-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/hozimurayama/multi-llm-debugging-bridge/tool-review"><img src="https://agentmods.dev/badge/skills/hozimurayama/multi-llm-debugging-bridge/tool-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 395 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 $0.00026 $0.00395
Opus 5 $0.00013 $0.00198
Sonnet 5 $0.00005 $0.00079
Haiku 4.5 $0.00003 $0.00040

Measured 9d ago against content hash 50d947685f39, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

tool-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 9d 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-review — 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/skills/tool-review/SKILL.md · 54 lines

What it actually says

Tool Review

Review the MCP tool implementation for: $ARGUMENTS

Process

1. Locate the tool

Find the tool implementation in src/tools/ and its registration in src/server.ts.

2. Check against project patterns

Verify each of these (from CLAUDE.md):

Response format:

  • Returns { content: [{ type: 'text', text: '...' }] } on success
  • Returns { content: [{ type: 'text', text: 'Error: ...' }], isError: true } on error

Input validation:

  • Required arguments are checked with clear error messages
  • Uses appropriate types from Zod schemas where applicable

Registration in server.ts:

  • Tool is imported with .js extension in the import path
  • Added to getTools() array with correct JSON Schema for inputs
  • Has a case in the CallToolRequestSchema handler switch

Dependencies:

  • Uses the right dependencies (providerManager, conversationManager, healthMonitor, etc.)
  • Follows the same injection pattern as existing tools

3. Check for common issues

  • Missing error handling for provider calls
  • Hardcoded values that should come from config
  • Missing or incorrect TypeScript types
  • Security issues (unsanitized input, injection risks)

4. Report

For each check:

  • ✓ Pass — follows the pattern correctly
  • ✗ Fail — what's wrong and how to fix it
  • ⚠ Warning — works but could be improved

End with a summary: APPROVED or NEEDS CHANGES with specific action items.

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. 9d ago First seen · 54 lines · 26 tokens per session scan A 50d947685f39

Subscribe to this mod's changes

tool-review is a skill published in the GitHub repository HoziMurayama/Multi-LLM-Debugging-Bridge (5 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 395 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to tool-review, differing in 0 lines, and is treated as a copy.