xiaozhi-mcphub: Skill for Claude Code

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

release-notes is a skill for Claude Code from huangjunsen0406/xiaozhi-mcphub. It costs 58 tokens per session (1,373 once invoked), scanned A, a copy of release-notes, Apache-2.0.

A workflow for rewriting an existing GitHub release note, the summary published with a software version, into a bilingual English-and-Chinese template. It builds the references section from merged pull requests.

In plain words
What is it for?
Editing release bodies, organizing features and fixes, recording breaking changes and contributors, and adding pull-request references.
Why use it?
It turns automatically generated release text into the project’s required structure and language format.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is huangjunsen0406/xiaozhi-mcphub's own configuration. It tells Claude Code how to work on xiaozhi-mcphub 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 xiaozhi-mcphub configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node scripts/validate-release-notes.js /tmp/release-notes-<tag>.md.

Reuse

Borrowing it

Nothing to install: this file belongs to huangjunsen0406/xiaozhi-mcphub. 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/huangjunsen0406/xiaozhi-mcphub/main/.claude/skills/release-notes/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/huangjunsen0406/xiaozhi-mcphub

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-notes

README.md
[![agentmods](https://agentmods.dev/badge/skills/huangjunsen0406/xiaozhi-mcphub/release-notes/github.svg)](https://agentmods.dev/skills/huangjunsen0406/xiaozhi-mcphub/release-notes)
Your own site
<a href="https://agentmods.dev/skills/huangjunsen0406/xiaozhi-mcphub/release-notes"><img src="https://agentmods.dev/badge/skills/huangjunsen0406/xiaozhi-mcphub/release-notes/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 release-notes

Your own site · 80×15
<a href="https://agentmods.dev/skills/huangjunsen0406/xiaozhi-mcphub/release-notes"><img src="https://agentmods.dev/badge/skills/huangjunsen0406/xiaozhi-mcphub/release-notes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,373 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 100% 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 $0.00058 $0.01373
Opus 5 $0.00029 $0.00687
Sonnet 5 $0.00012 $0.00275
Haiku 4.5 $0.00006 $0.00137

Measured 9d ago against content hash ed2adc9ebefa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

release-notes 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 9d 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

100% identical to release-notes — 0 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-notes/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release Notes

Rewrite an existing GitHub release's body into the project's bilingual template, then push it back. The repo's release pipeline auto-generates a raw body on tag push (generate_release_notes: true) that does not match the bilingual template — this skill cleans it up.

Required structure

Every release body must follow this section order. Optional sections are omitted entirely when they have no content — never leave an empty section, never use None/ placeholders.

Section Required Chinese pair
## Summary yes (non-empty)
## Features optional ## 功能
## Fixes optional ## 修复
## Breaking Changes optional ## 破坏性变更
## 摘要 yes (non-empty) pair of Summary
## New Contributors optional (English only, no Chinese pair)
## References yes (non-empty)

Rules enforced by scripts/validate-release-notes.js (CI runs it on publish/edit):

  • Summary, 摘要, References must be present and non-empty.
  • Each optional English section and its Chinese pair must appear together — having one without the other fails validation.
  • Optional sections with no real content are omitted, not stubbed.

Workflow

  1. Resolve the target release.

    • If the user gave a tag (e.g. v1.0.14), use it.
    • Otherwise use the latest: gh release list --limit 1.
  2. Fetch the existing body.

    • gh release view <tag> --json body -q .body
    • Read it to find an existing Full changelog: ...compare/<prev>...<tag> line to learn the previous tag. Also note any PR list already present, but do not trust it blindly — re-fetch authoritatively in step 4.
  3. Resolve the previous tag (the compare range).

    • Preferred: parse compare/vX...vY from the existing body.
    • Fallback: git describe --tags --abbrev=0 <tag>^ to get the tag before <tag>.
    • First-ever tag (no previous tag exists): fetch all merged PRs up to the tag date; if more than 50, take the 50 most recent and flag it for the user to review.

Read the full file on GitHub · 87 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. 9d ago First seen · 87 lines · 58 tokens per session scan A ed2adc9ebefa

Subscribe to this mod's changes

release-notes is a skill published in the GitHub repository huangjunsen0406/xiaozhi-mcphub (192 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 58 tokens to every session and 1,373 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to release-notes, differing in 0 lines, and is treated as a copy.