agentmods.dev

grafana-mcp: Instructions file for Claude Code

CLAUDE.md

grafana-mcp CLAUDE.md is an instructions file for Claude Code from ninanung/grafana-mcp. It costs 711 tokens per session, scanned A, original, MIT.

A set of instructions for keeping English and Korean README files accurate when a project changes. A README is the main usage and setup document for a software project.

In plain words
What is it for?
Checking README files after code or configuration changes, updating installation and usage examples, comparing the English and Korean versions, and recording what was reviewed.
Why use it?
Documentation can become misleading when code, commands, settings, or error messages change. These instructions require a full comparison and verification before commits and releases.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions Claude Code.

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

not rated 0repo changed 10d ago A scan 711 tokens original MIT
View source ↗ ninanung/grafana-mcp
Reuse

Borrowing it

Nothing to install: this file belongs to ninanung/grafana-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/ninanung/grafana-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ninanung/grafana-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 grafana-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ninanung/grafana-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/ninanung/grafana-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ninanung/grafana-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ninanung/grafana-mcp/claude-md/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 grafana-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ninanung/grafana-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ninanung/grafana-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 711 This file is loaded in full into every session.
When invoked 711 The same file — it is already loaded in full.
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 $0.00711 $0.00711
Opus 5.5 $0.00284 $0.00284
Sonnet 5.5 $0.00142 $0.00142
Haiku 4.5 $0.00071 $0.00071

Measured 10d ago against content hash 4269c5320915, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

grafana-mcp CLAUDE.md 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.md · 28 lines

What it actually says

grafana-mcp

README 동기화 — 변경이 생기면 반드시 line by line 대조 후 같이 수정

repo 에 변경(코드·설정 형식·패키지 메타·툴 동작·에러/안내 문구 등)이 생기면, 커밋 전에 아래 절차로 README.md / README_kr.md 를 확인하고 필요한 수정을 같은 커밋에 포함한다. 대상 영역 목록은 .claude/rules/readme-update-rule.md 를 따르고, 확인 방법은 이 절차가 우선한다.

절차

  1. 변경 전후 목록화 — git diff(커밋 전) 또는 git diff <직전 릴리즈 태그>..HEAD(릴리즈 전)로 바뀐 것을 항목으로 뽑는다: 툴 추가·삭제·인자, 동작·출력·에러 메시지, 환경변수, 설정 파일 형식·위치, 실행·등록 방법, 캐시·로그 포맷, 안전장치.
  2. README 전체를 line by line 으로 대조 — 처음부터 끝까지 모든 줄을 읽고, 각 줄이 1의 변경 후 상태와 맞는지 판정한다. 변경과 관련된 섹션만 골라 읽지 않는다.
    • 추가만으로 끝내지 않는다. 새 기능 설명을 덧붙이는 것과 별개로, 변경 때문에 틀려졌거나 더 이상 권장 방식이 아닌 기존 줄(설치·설정 예시 JSON, CLI 명령, 표, 사용 예시, 캐시·안전장치 설명)을 찾아 고친다.
    • 설정·설치 예시는 실제 동작으로 검증한다. 설정 파일 위치·스코프(예: Claude Code 는 user 스코프가 ~/.claude.json, 프로젝트 공유가 루트 .mcp.json), CLI 플래그, JSON 키는 추측하지 않고 CLI --help·실제 실행 결과·코드로 확인한다.
  3. 영문/한글 대조 — README.md 와 README_kr.md 를 같은 섹션·같은 줄 단위로 비교해 정보·섹션 순서· 예시가 일치하는지 확인한다. 한쪽에만 있는 정보를 남기지 않는다.
  4. 결과 보고 — 작업 보고에 README 확인 결과를 남긴다. 수정한 줄, 또는 "반영할 것 없음"이면 대조한 섹션 범위를 적는다. ("확인 안 함"과 "확인했고 반영할 것 없음"을 구분하기 위함)
  5. 릴리즈 직전 재확인 — 버전 bump·릴리즈 태그 push 전에는 직전 릴리즈 태그 이후 전체 diff 기준으로 1~3 을 다시 한다. 커밋 단위 확인에서 빠진 것이 릴리즈 단위에서 잡히도록 하기 위함. 배포 절차 전체는 npm-release 스킬(.claude/skills/npm-release/SKILL.md)을 따른다.
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 Changed · +1 lines · +31 tokens per session 4269c5320915
  2. 23d ago First seen · 27 lines · 680 tokens per session scan A d2c26d37fba9

Subscribe to this mod's changes

grafana-mcp CLAUDE.md is an instructions file published in the GitHub repository ninanung/grafana-mcp (0 stars, last pushed 11d ago), licensed MIT. It adds 711 tokens to every session, about $0.0028 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 2026-10-15.

Project managementWriting and docs
Related

grafana-mcp CLAUDE.md compared with instructions from other repositories

grafana-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
grafana-mcp CLAUDE.mdninanung/grafana-mcpInstructions file011d agoMITA711Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode