neosql-mcp: Skill for Claude Code

.agents/skills/release/SKILL.md

release is a skill for Claude Code, Codex from unvus/neosql-mcp. It costs 136 tokens per session (2,772 once invoked), scanned A, original, Apache-2.0.

A release procedure that recommends a package version from unpublished changes, then waits for approval before creating the version, commit, and tag.

In plain words
What is it for?
Use it to prepare an npm package release and push its approved commit and tag so the repository's workflow can publish it.
Why use it?
It checks the branch, working tree, existing tags, package version, registry version, and publishing workflow before releasing, reducing accidental or unexplained releases.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions .claude-plugin; installed under .agents/ (shared by several agents).

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

Reuse

Borrowing it

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

Made for: Claude Code, Codex.

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/unvus/neosql-mcp/release/github.svg)](https://agentmods.dev/skills/unvus/neosql-mcp/release)
Your own site
<a href="https://agentmods.dev/skills/unvus/neosql-mcp/release"><img src="https://agentmods.dev/badge/skills/unvus/neosql-mcp/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 release

Your own site · 80×15
<a href="https://agentmods.dev/skills/unvus/neosql-mcp/release"><img src="https://agentmods.dev/badge/skills/unvus/neosql-mcp/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 136 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,772 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 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 $0.00136 $0.02772
Opus 5.5 $0.00054 $0.01109
Sonnet 5.5 $0.00027 $0.00554
Haiku 4.5 $0.00014 $0.00277

Measured 1mo ago against content hash 72ec53bb09de, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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.

.agents/skills/release/SKILL.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release

미배포 변경을 기준으로 버전을 추천하고, 사용자가 확정한 버전으로 npm version을 실행한 뒤 commit과 tag를 push한다. tag push가 .github/workflows/publish.yml을 트리거해 npm publish와 plugin 브랜치 전진을 자동으로 수행하므로, 이 스킬은 로컬에서 수동 publish를 하지 않는다.

스킬 실행 요청만으로 추천 버전을 확정하지 않는다. 사용자가 버전이나 증가 종류를 승인하거나 지정한 뒤에만 npm version과 push를 실행한다. 상세 배포 원칙은 docs/npm-publish.md의 "버전과 태그", "Plugin 릴리스" 절이 기준이다.

1. 상태 확인

아래를 한 번에 확인하고 문제가 있으면 멈춘다.

git status --short --branch
git fetch origin --tags
git log --oneline "$(git describe --tags --abbrev=0 --match 'v*')..HEAD"
node -p "require('./package.json').version"
npm view neosql-mcp version
  • 브랜치가 main이 아니면 중단하고 확인한다. release tag는 main에서만 만든다.
  • working tree가 clean이 아니면 중단한다. release commit에 섞이면 안 되는 변경을 대신 commit하거나 stash하지 않는다. 사용자에게 정리 여부를 묻는다.
  • origin/main보다 뒤처져 있으면 중단한다. 먼저 pull이 필요한지 사용자와 확인한다.
  • package.json 버전, 최신 v* tag, npm registry의 latest 세 값이 서로 다르면 왜 다른지 설명할 수 있어야 한다. 설명이 안 되면 추측해서 올리지 않는다.
  • publish workflow가 v* tag push로 트리거되는지 .github/workflows/publish.yml에서 다시 확인한다. workflow가 바뀌어 있으면 이 스킬의 절차보다 workflow를 우선한다.

2. 변경 분석과 버전 추천

최신 v* tag 이후 HEAD까지의 commit을 조사한다. 제목만 보지 말고 필요한 diff를 본다. 이 패키지에서 사용자에게 배포되는 것은 dist/(즉 src/), README.md, LICENSE, npm-shrinkwrap.json, 그리고 plugins/neosql-mcp/다. 이 범위에 영향이 없는 변경(내부 문서, 테스트, CI)만 있으면 배포가 필요 없다고 말한다.

추천 기준. 최종 선택은 사용자에게 있다.

  • patch X.Y.Z → X.Y.(Z+1): 오류 수정, 문구·문서 변경, README 변경, package.json 메타데이터 변경, 의존성 보안 업데이트, 동작이 같은 리팩터링. README와 package.json은 npm 페이지에 그대로 노출되므로 문서만 바뀌어도 publish 가치가 있다.
  • minor X.Y.Z → X.(Y+1).0: 새 MCP tool, 새 CLI 옵션, 기존 tool의 입력·출력 확장, 새 MCP host 지원처럼 사용자가 체감하는 기능 추가. patch와 minor가 섞이면 minor.
  • major X.Y.Z → (X+1).0.0: tool 이름·입력 스키마·응답 형식 변경, CLI 옵션 제거, 지원 Node 버전 상향, upstream 계약 변경처럼 기존 MCP host 설정이나 Desktop 버전과 호환이 깨질 때. 사용자는 호환성 파괴가 없어도 제품 판단으로 major를 고를 수 있다.
  • commit type 접두어(feat/fix)는 참고일 뿐이다. docs:로 표시된 README 변경도 배포 대상이고, feat:로 표시된 내부 리팩터링은 patch일 수 있다.

다음을 한 번에 제시하고 응답을 기다린다.

Read the full file on GitHub · 156 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. 1mo ago Changed · +4 lines 72ec53bb09de
  2. 1mo ago First seen · 152 lines · 136 tokens per session scan A 3e209eb0ce0d

Subscribe to this mod's changes

release is a skill published in the GitHub repository unvus/neosql-mcp (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 136 tokens to every session and 2,772 once invoked, about $0.0005 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 2026-09-30.

Related

release compared with skills from other repositories

release next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
releaseunvus/neosql-mcpSkill23d agoApache-2.0A136Claude Code, Codex
release-announcementpaperclipai/paperclipSkill111kyesterdayMITA42Claude Code, Codex
releasethedotmack/claude-memSkill114kyesterdayApache-2.0A13Claude Code
release-notesphuryn/pm-skillsSkill28k8d agoMITA57Claude Code
multi-agent-release-managerchromium/chromiumSkill25kyesterdayBSD-3-ClauseA27Claude Code, Codex
pack-submitaeonfun/aeonSkill788yesterdayMITA27Claude Code, Codex
updater_guidesiddsachar/row-botSkill1.7kyesterdayApache-2.0A22Claude Code, Codex