apple-mail-mcp: Skill for Claude Code

.claude/skills/release/SKILL.md

release is a skill for Claude Code from LeChabrax/apple-mail-mcp. It costs 49 tokens per session (1,286 once invoked), scanned A, a copy of release, MIT.

A skill for coordinating a software release from milestone checks through version updates, changelog creation, validation, tagging, and pull-request creation. A milestone is a group of issues planned for a particular release.

In plain words
What is it for?
Use it when releasing a new version, planning a release, or managing version numbers.
Why use it?
It gives release work a defined sequence and checks that planned issues, version references, tests, and review steps are handled before publishing.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

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

Reuse

Borrowing it

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/lechabrax/apple-mail-mcp/release.svg)](https://agentmods.dev/skills/lechabrax/apple-mail-mcp/release)
Your own site
<a href="https://agentmods.dev/skills/lechabrax/apple-mail-mcp/release"><img src="https://agentmods.dev/badge/skills/lechabrax/apple-mail-mcp/release.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,286 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 86% copy Near-identical to another mod 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 $0.00049 $0.01286
Opus 5 $0.00024 $0.00643
Sonnet 5 $0.00010 $0.00257
Haiku 4.5 $0.00005 $0.00129

Measured 7d ago against content hash 192aad8c2292, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

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 7d 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.

Origin

This is a copy

86% identical to release — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/skills/release/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release Workflow (12 Phases)

Phase 1: Milestone Check

  • List open milestones via gh api
  • Verify 0 open issues in target milestone
  • Stop if issues remain (ask user to move/close)

Phase 2: Version Number

  • Read current version from pyproject.toml (authoritative)
  • Milestone title = target version
  • Confirm with user

Phase 3: Create Release Branch

  • git checkout -b release/vX.Y.Z from main

Phase 4: Bump Version

Update ALL files (pyproject.toml is authoritative):

  1. pyproject.tomlversion = "X.Y.Z"
  2. src/apple_mail_mcp/__init__.py__version__ = "X.Y.Z"
  3. .claude/CLAUDE.md**Version:** vX.Y.Z
  4. README.md — all version references

Phase 5: Generate CHANGELOG

  • Commits since last tag: git log v{prev}..HEAD --oneline
  • PRs since last release: gh pr list --state merged --search "merged:>YYYY-MM-DD"
  • Keep a Changelog format: ## [X.Y.Z] - YYYY-MM-DD
  • Categories: Added, Changed, Fixed, Removed

Phase 6: Test Coverage Review

  • Run coverage: make coverage
  • Compare against fail_under in pyproject.toml
  • Audit changed files for adequate coverage

Phase 7: Code Review

  • Launch superpowers:code-reviewer against cumulative diff
  • Critical issues block release

Phase 8: Documentation Review

  • README, CLAUDE.md, CHANGELOG, docs/**, tool docstrings, skills
  • The content-drift gate (check_docs.sh, Phase 9) automates the tool-set / removed-name / cross-ref / eval-description-sync parts; this phase is the human read for things it can't check (accuracy, tone, completeness).

Phase 8.5: Refresh derived artifacts (mandatory, #288)

Derived artifacts rot silently between releases — refresh them against the release commit so a stale snapshot can't ship:

  1. make eval-descriptions — regenerate the blind-eval tool descriptions; commit if changed. (check_docs.sh also fails on drift here.)
  2. Re-capture the benchmark baseline (#216): MAIL_TEST_MODE=true MAIL_TEST_ACCOUNT=<acct> uv run pytest tests/benchmarks/ --run-benchmark --capture-baseline (needs real Mail.app); commit the refreshed baseline.json.
  3. Re-run the blind agent eval (#219) and refresh its scored snapshot (needs OPENROUTER_API_KEY); commit.

Read the full file on GitHub · 99 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. 7d ago First seen · 99 lines · 49 tokens per session scan A 192aad8c2292

Subscribe to this mod's changes

release is a skill published in the GitHub repository LeChabrax/apple-mail-mcp (0 stars, last pushed 4d ago), licensed MIT. It adds 49 tokens to every session and 1,286 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to release, differing in 4 lines, and is treated as a copy.