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.
curl -O https://raw.githubusercontent.com/chainapsis/keplr-wallet-mcp/develop/.claude/skills/mcp-tool-validator/SKILL.mdgit clone --depth 1 https://github.com/chainapsis/keplr-wallet-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/skills/chainapsis/keplr-wallet-mcp/mcp-tool-validator)<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.
<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>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 | $0.00065 | $0.01674 |
| Opus 5 | $0.00032 | $0.00837 |
| Sonnet 5 | $0.00013 | $0.00335 |
| Haiku 4.5 | $0.00006 | $0.00167 |
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.
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
- 대상 코드 읽기
- 체크리스트 항목별 검증
- 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 |
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.
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.
- 10d ago First seen · 239 lines · 65 tokens per session scan A d510c1de2f20
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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…