mcp-grafana: Skill for Claude Code

.claude/skills/draft-release/SKILL.md

draft-release is a skill for Claude Code from grafana/mcp-grafana. It costs 25 tokens per session (1,511 once invoked), scanned A, original, Apache-2.0.

A release-preparation workflow for the mcp-grafana project. It updates the version, builds a changelog from Git history, creates a release branch, and opens a pull request.

In plain words
What is it for?
Use it when preparing a major, minor, or patch release of mcp-grafana.
Why use it?
It organizes the repeated work of preparing a release and keeps the release changes reviewable before they are merged.

Skill for Claude Code ✓ vendor

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

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

Part of the grafana plugin — 1 skill, 1 MCP server shipped together

About the project

grafana/mcp-grafana is a Model Context Protocol server that lets AI clients access and manage Grafana resources such as dashboards. Grafana users can connect it to an MCP client to search, inspect, create, and update dashboards and related data. The catalogue includes an MCP integration, plugin, and skill for operating Grafana through this server.

grafana/mcp-grafana · 3,437 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to grafana/mcp-grafana. 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/grafana/mcp-grafana/main/.claude/skills/draft-release/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/grafana/mcp-grafana

Made for: Claude Code.

Or install grafana, the plugin that ships this one along with the rest of its 1 skill, 1 MCP server.

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 draft-release

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/grafana/mcp-grafana/draft-release"><img src="https://agentmods.dev/badge/skills/grafana/mcp-grafana/draft-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,511 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00025 $0.01511
Opus 5 $0.00013 $0.00756
Sonnet 5 $0.00005 $0.00302
Haiku 4.5 $0.00003 $0.00151

Measured 10d ago against content hash b909f67cc950, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

draft-release 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/draft-release/SKILL.md · 176 lines

How it starts

The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Draft Release

You are creating a new release for the mcp-grafana project. The user has provided a bump level: major, minor, or patch.

How the release pipeline works

  1. This skill creates a release/v* branch with a CHANGELOG.md update and opens a PR
  2. When the PR is merged, the auto-tag.yml workflow automatically creates the git tag
  3. The tag triggers release.yml (goreleaser → GitHub Release + binaries) and docker.yml (Docker images + MCP Registry)

Your job is step 1 only. Do NOT create tags manually.

Step 1: Determine the new version

  1. Get the latest semver tag:
    git tag --sort=-version:refname | head -1
    
  2. Parse the tag as vMAJOR.MINOR.PATCH and bump according to the argument:
    • major → increment MAJOR, reset MINOR and PATCH to 0
    • minor → increment MINOR, reset PATCH to 0
    • patch → increment PATCH
  3. The new version string is v<MAJOR>.<MINOR>.<PATCH> (e.g. v0.11.0). The previous tag is the "from" ref.

Step 2: Create the release branch

git checkout main
git pull origin main
git checkout -b release/v<NEW_VERSION>

Step 3: Gather and categorize commits

Run:

git log <PREV_TAG>..HEAD --no-merges --format="%H %s"

For each commit, categorize by its conventional commit prefix:

Prefix CHANGELOG Section
feat Added
fix (security-related) Security
fix Fixed
refactor, perf Changed
BREAKING CHANGE or !: Removed (or note as breaking in relevant section)

Skip these commits entirely:

  • chore(deps) — dependency bumps
  • chore commits that only touch CI config, GitHub Actions, or similar
  • docs commits that only update README or non-user-facing docs
  • test commits that only add/fix tests
  • ci commits

Step 4: Write human-readable entries

For each significant commit:

  1. Read the full commit message: git log <hash> -1 --format="%B"
  2. Extract the PR number from the commit message (look for (#NNN) in the subject or a PR: line)
  3. Derive the repo URL: git remote get-url origin → extract https://github.com/<org>/<repo>
  4. Write a concise, human-readable description of the change (not just the commit subject). Focus on what the user gains.
  5. Format as: - Description of the change ([#NNN](https://github.com/<org>/<repo>/pull/NNN))

Read the full file on GitHub · 176 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. 10d ago First seen · 176 lines · 25 tokens per session scan A b909f67cc950

Subscribe to this mod's changes

draft-release is a skill published in the GitHub repository grafana/mcp-grafana (3,437 stars, last pushed today), licensed Apache-2.0. It adds 25 tokens to every session and 1,511 once invoked, about $0.0001 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 2026-08-30.