keplr-wallet-mcp: Skill for Claude Code

.claude/skills/mcp-tool-validator/SKILL.md

mcp-tool-validator is a skill for Claude Code from chainapsis/keplr-wallet-mcp. It costs 65 tokens per session (1,674 once invoked), scanned A, original, MIT.

A code-review checklist for MCP tools, which are functions exposed to an AI agent through the Model Context Protocol.

In plain words
What is it for?
Use it to inspect tool implementations, including parameter descriptions, defaults, type limits, JSON responses, error flags, and suggested follow-up actions.
Why use it?
It helps catch unclear input schemas, inconsistent responses, and missing error handling before an MCP tool is used.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is chainapsis/keplr-wallet-mcp's own configuration. It tells Claude Code how to work on keplr-wallet-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 keplr-wallet-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to chainapsis/keplr-wallet-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/chainapsis/keplr-wallet-mcp/develop/.claude/skills/mcp-tool-validator/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/chainapsis/keplr-wallet-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 mcp-tool-validator

README.md
[![agentmods](https://agentmods.dev/badge/skills/chainapsis/keplr-wallet-mcp/mcp-tool-validator/github.svg)](https://agentmods.dev/skills/chainapsis/keplr-wallet-mcp/mcp-tool-validator)
Your own site
<a href="https://agentmods.dev/skills/chainapsis/keplr-wallet-mcp/mcp-tool-validator"><img src="https://agentmods.dev/badge/skills/chainapsis/keplr-wallet-mcp/mcp-tool-validator/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 mcp-tool-validator

Your own site · 80×15
<a href="https://agentmods.dev/skills/chainapsis/keplr-wallet-mcp/mcp-tool-validator"><img src="https://agentmods.dev/badge/skills/chainapsis/keplr-wallet-mcp/mcp-tool-validator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,674 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 $0.00065 $0.01674
Opus 5 $0.00032 $0.00837
Sonnet 5 $0.00013 $0.00335
Haiku 4.5 $0.00006 $0.00167

Measured 10d ago against content hash d510c1de2f20, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mcp-tool-validator 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 10d 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/skills/mcp-tool-validator/SKILL.md · 239 lines

How it starts

The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Tool Validator

MCP 도구 구현 코드를 검증하고 개선점을 제안하는 스킬.

검증 워크플로우

  1. 대상 코드 읽기
  2. 체크리스트 항목별 검증
  3. 검증 보고서 출력

검증 체크리스트

1. 스키마 검증

항목 검증 내용
describe() 모든 파라미터에 설명이 있는가?
기본값 optional() 필드에 default() 제공되는가?
타입 제약 min(), max(), enum() 등 제약 조건 적절한가?
Zod import zod 올바르게 import하는가?
// ❌ 나쁜 예
inputSchema: {
  chain: z.string(),
  amount: z.string(),
}

// ✅ 좋은 예
inputSchema: {
  chain: z.string().describe("Chain ID or name (e.g., 'cosmoshub-4', 'cosmos')"),
  amount: z.string().describe("Amount with denom (e.g., '1 ATOM', '1.5')"),
}

2. 응답 구조 검증

항목 검증 내용
JSON 형식 JSON.stringify(data, null, 2) 사용하는가?
일관된 구조 status, data, error 필드 일관성
isError 에러 시 isError: true 반환하는가?
suggestedActions 조회 결과에 다음 액션 제안 포함하는가?
// ✅ 좋은 응답 구조
return {
  content: [{
    type: "text",
    text: JSON.stringify({
      status: "success",
      data: { /* ... */ },
      suggestedActions: [
        { tool: "delegate", reason: "Stake to earn rewards", priority: 1 },
      ],
    }, null, 2),
  }],
};

3. 에러 처리 검증

항목 검증 내용
try-catch 비동기 작업이 try-catch로 감싸져 있는가?
에러 분류 classifyError() 사용하는가?
복구 제안 에러에 suggestion, retryAction 포함하는가?
Setup Required 설정 필요 시 에러 대신 안내 반환하는가?
// ✅ 좋은 에러 처리
try {
  const result = await riskyOperation();
  return { content: [/* ... */] };
} catch (error) {
  const classified = classifyError(error);
  return {
    content: [{
      type: "text",
      text: JSON.stringify({
        isError: true,
        category: classified.category,
        message: classified.message,
        suggestion: classified.suggestion,
      }, null, 2),
    }],
    isError: true,
  };
}

4. Tool Annotations 검증

Annotation 사용 시점
readOnlyHint: true 상태 변경 없는 조회 도구
destructiveHint: true 삭제, 전송 등 위험한 작업
idempotentHint: true 반복 호출해도 동일 결과
openWorldHint: true 블록체인/외부 API 호출

Read the full file on GitHub · 239 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 239 lines · 65 tokens per session scan A d510c1de2f20

Subscribe to this mod's changes

mcp-tool-validator is a skill published in the GitHub repository chainapsis/keplr-wallet-mcp (5 stars, last pushed 4mo ago), licensed MIT. It adds 65 tokens to every session and 1,674 once invoked, about $0.0003 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.