memradar: Skill for Claude Code

.claude/skills/release/SKILL.md

release is a skill for Claude Code from on1659/memradar. It costs 79 tokens per session (2,828 once invoked), scanned A, original, MIT.

A release workflow for publishing the memradar package to npm, a JavaScript package registry, and updating its GitHub repository.

In plain words
What is it for?
Use it when preparing a new memradar version, choosing a version change, running the test harness, publishing to npm, and pushing the release commit and tag.
Why use it?
It brings versioning, tests, package publishing, and GitHub tagging into one defined process, reducing missed release steps.

Skill for Claude Code

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

This is on1659/memradar's own configuration. It tells Claude Code how to work on memradar 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 memradar configures →

Reuse

Borrowing it

Nothing to install: this file belongs to on1659/memradar. 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/on1659/memradar/master/.claude/skills/release/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/on1659/memradar

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/on1659/memradar/release.svg)](https://agentmods.dev/skills/on1659/memradar/release)
Your own site
<a href="https://agentmods.dev/skills/on1659/memradar/release"><img src="https://agentmods.dev/badge/skills/on1659/memradar/release.svg" alt="Measured on agentmods" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,828 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00079 $0.02828
Opus 5 $0.00039 $0.01414
Sonnet 5 $0.00016 $0.00566
Haiku 4.5 $0.00008 $0.00283

Measured 4d ago against content hash 27ea433633f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 4d 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/release/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

memradar Release

This skill releases a new version of memradar to npm and pushes the version commit + tag to GitHub, in one flow. It is scoped to this repository (on1659/memradar).

Arguments

The skill may receive an argument string. Parse these tokens (any order, all optional):

  • Bump level: patch | minor | major | an explicit semver like 0.2.0
  • Flags: --skip-tests (skips npm run test:harness — use only if tests are already known green)
  • Anything else: treat as the release description (one-line commit message suffix)

If bump level is missing, ask the user via AskUserQuestion with options patch / minor / major. Also ask for a one-line description if it isn't in the args. Never guess either.

npm 인증 (안전 패턴 — 토큰이 로그에 안 남게)

이 레포의 실제 릴리스 경로는 로컬 npm publish 다 (GitHub Actions release.yml은 Actions 정책 차단으로 실패 — .github/workflows/release.yml 참고). 로컬 publish에는 npm 자동화 토큰이 필요한데, 과거 릴리스에서 토큰을 .npmrc에 평문으로 쓰거나 명령에 인라인해 세션 로그에 평문 유출된 사고가 있었다. 그래서 인증은 아래 패턴만 쓴다.

.npmrc (리터럴 토큰 미기록):

.npmrc(이미 .gitignore됨)에는 토큰 값 대신 환경변수 보간만 적는다. npm 10.9.4+ 가 ${VAR} 보간을 지원한다.

//registry.npmjs.org/:_authToken=${NPM_TOKEN}

이 한 줄이면 충분하다. 실제 토큰 문자열(npm_...)을 .npmrc에 절대 쓰지 않는다.

토큰 주입은 사용자가 자기 터미널에서 직접 (out-of-band):

토큰은 사용자만 자기 셸 환경변수로 주입한다. release 스킬을 실행하기 전에 사용자가 직접:

  • PowerShell: $env:NPM_TOKEN = '<토큰>'
  • bash/zsh: export NPM_TOKEN=<토큰>

Claude 도구 호출(Bash/PowerShell)로 토큰 값을 절대 전달하지 않는다. 토큰은 사용자 셸에만 존재하고, 스킬은 그 환경변수가 npm에 의해 ${NPM_TOKEN}으로 읽히게만 한다. 도구 호출이 캡처되는 세션 로그에는 토큰 값이 한 글자도 들어가지 않는다.

금지 명령 (절대 실행 금지 — Safety rules와 동급):

  • echo //registry.npmjs.org/:_authToken=npm_... >> .npmrc 또는 어떤 형태로든 토큰 .npmrc에 쓰는 명령 — 토큰이 도구 호출 인자로 로그에 박힌다.
  • npm config set //registry.npmjs.org/:_authToken=npm_... — 동일한 이유로 금지.
  • npm publish --//registry.npmjs.org/:_authToken=npm_... (또는 --registry/--auth-token 인라인) — publish 명령에 토큰을 붙이지 않는다.
  • echo $NPM_TOKEN / echo $env:NPM_TOKEN / cat .npmrc (또는 Get-Content .npmrc) — 토큰 을 stdout으로 출력하는 명령. 존재 확인은 값 노출 없이 boolean으로만 (아래 프리플라이트 참고).

Read the full file on GitHub · 131 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. 4d ago First seen · 131 lines · 79 tokens per session scan A 27ea433633f9

Subscribe to this mod's changes

release is a skill published in the GitHub repository on1659/memradar (11 stars, last pushed 5d ago), licensed MIT. It adds 79 tokens to every session and 2,828 once invoked, about $0.0004 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 2026-09-02.