safebreach-mcp: Skill for Claude Code

.claude/skills/mcp-create-release/SKILL.md

mcp-create-release is a skill for Claude Code from SafeBreach/safebreach-mcp. It costs 60 tokens per session (2,003 once invoked), scanned A, original, BSD-3-Clause.

A release-preparation skill for SafeBreach MCP servers. MCP servers provide AI tools with a standard connection to external services.

In plain words
What is it for?
Use it when preparing a new MCP release: it checks the repository, asks which version increment to apply, updates pyproject.toml, builds a changelog from Git history, and opens a GitHub PR.
Why use it?
It coordinates the version update, changelog creation, and GitHub pull request needed for a release candidate.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: names the AskUserQuestion tool.

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

Reuse

Borrowing it

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/safebreach/safebreach-mcp/mcp-create-release"><img src="https://agentmods.dev/badge/skills/safebreach/safebreach-mcp/mcp-create-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,003 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 $0.00060 $0.02003
Opus 5 $0.00030 $0.01001
Sonnet 5 $0.00012 $0.00401
Haiku 4.5 $0.00006 $0.00200

Measured 12d ago against content hash b2b69f23c862, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

mcp-create-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 12d 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-create-release/SKILL.md · 230 lines

How it starts

The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create MCP Release

Prepare a release candidate for the SafeBreach MCP servers. Bumps version in pyproject.toml, generates changelog from git history, and creates a GitHub PR.

Step 1: Validate Environment

  1. Read pyproject.toml in the repo root — confirm it contains name = "safebreach-mcp-server". If not found, halt: "This command must be run from the safebreach-mcp repository root."
  2. Check working tree is clean:
    git status --porcelain
    
    If dirty, present options via AskUserQuestion:
    • "Stash changes" — run git stash push --include-untracked -m "pre-release stash" then continue (the --include-untracked flag is required to capture new/untracked files, not just modified ones)
    • "Abort" — stop the workflow

Step 2: Ask Version Bump Type

Present the choice via AskUserQuestion:

  • Minor — increment minor version, reset patch (e.g., 1.1.0 → 1.2.0)
  • Major — increment major version, reset minor and patch (e.g., 1.1.0 → 2.0.0)

Step 3: Determine Current Version and Calculate Next

  1. Read pyproject.toml and extract the version field from line 3 (format: version = "X.Y.Z")
  2. Parse into major, minor, patch integers
  3. Apply the bump:
    • Minor: increment minor, set patch to 0
    • Major: increment major, set minor and patch to 0
  4. Display: Version: {current} → {next}

Step 4: Create Release Branch

  1. Ensure on main with latest:
    git checkout main && git pull origin main
    
  2. Construct branch name: release_{next_version} (e.g., release_1.2.0)
  3. Check if branch already exists:
    git branch -a --list "*release_{next_version}*"
    
  4. If it exists, ask the user via AskUserQuestion:
    • "Use existing branch" — checkout the existing branch
    • "Create with suffix" — use release_{next_version}-v2
    • "Abort" — stop the workflow
  5. Create and checkout: git checkout -b {branch_name}

Step 5: Bump Version

Use the Edit tool to update pyproject.toml line 3, changing the old version string to the new one:

version = "{current}" → version = "{next}"

Read the full file on GitHub · 230 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. 12d ago First seen · 230 lines · 60 tokens per session scan A b2b69f23c862

Subscribe to this mod's changes

mcp-create-release is a skill published in the GitHub repository SafeBreach/safebreach-mcp (7 stars, last pushed yesterday), licensed BSD-3-Clause. It adds 60 tokens to every session and 2,003 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.