Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/narlei/claudecodenotify/releasenpx skills add narlei/claudecodenotify --skill releasegit clone --depth 1 https://github.com/narlei/claudecodenotifyWrote 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.
[](https://agentmods.dev/skills/narlei/claudecodenotify/release)<a href="https://agentmods.dev/skills/narlei/claudecodenotify/release"><img src="https://agentmods.dev/badge/skills/narlei/claudecodenotify/release.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00147 | $0.00894 |
| Opus 5 | $0.00073 | $0.00447 |
| Sonnet 5 | $0.00029 | $0.00179 |
| Haiku 4.5 | $0.00015 | $0.00089 |
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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release ClaudeCodeNotify
Publish a new GitHub release: build the artifacts, tag the version from
Resources/Info.plist, and create the release with release_notes.md as the body.
What a release consists of
- Version —
CFBundleShortVersionStringinResources/Info.plist(e.g.1.0.3). This is the single source of truth; the git tag and release title are derived from it. - Tag —
v<version>(e.g.v1.0.3), annotated, pushed toorigin. - Artifacts — produced by
make release:dist/ClaudeCodeNotify.dmg— stable name (the website's "latest" download link depends on it).dist/ClaudeCodeNotify-<version>.zip— versioned zip.
- Notes — the contents of
release_notes.mdat the repo root become the release body.
How to run it
The whole flow is bundled in scripts/create-release.sh. It is idempotent-safe: it refuses to run if the tag already exists, so you never double-publish a version.
Always dry-run first so the user can see exactly what will happen:
.claude/skills/release/scripts/create-release.sh --dry-run
Show the user the planned version, tag, artifacts, and notes preview. Once they confirm, run it for real:
.claude/skills/release/scripts/create-release.sh
Before you publish — checklist
Releases are public and irreversible-ish (deleting a release/tag is messy), so verify before running for real:
- Version is bumped. If
v<version>already exists, the version inInfo.plistwas not bumped — point this out and ask the user to bump it (and the Homebrew tap, if relevant) rather than forcing the tag. - The release commit is on the intended branch and pushed. The tag is created at
HEAD. If the user is on a feature branch (notmain), confirm that's intentional — most releases should be cut from the default branch with everything merged and pushed. release_notes.mdreflects this version. Skim it; if it still mentions an old version or stale install steps, fix it (or ask the user) before publishing.- Working tree is clean. Uncommitted changes won't be in the release. The script warns but doesn't block — surface the warning to the user.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 70 lines · 147 tokens per session scan A 4a8846efc2c0
release is a skill published in the GitHub repository narlei/claudecodenotify (10 stars, last pushed 2mo ago), licensed MIT. It adds 147 tokens to every session and 894 once invoked, about $0.0007 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.
Other skills, from other repositories
release
发布 Usage4Claude 新版本时使用。当用户说“发布新版本 / 发版 / 出新版 / release / 打 tag 发布 / 准备发版材料”等，用本 skill 引导完成从收集变更、编写 CHANGELOG 与 RELEASENOTES、更新版本号、编译验证，到发版 commit、CI 自动发布的完整流程。.
codex-changelog
This skill should be used when the user asks to check for new Codex CLI (codex-cli) releases, "what changed in Codex", "any Codex updates", "check codex releases", "diff the codex version", or wants Codex CLI releases reviewed for changes relevant to THIS repo's Codex bridge. Reads a locally-stored last-checked…
release-app-store-changelog
Create user-facing App Store release notes from git history. Use when asked to generate release changelog, App Store "What's New" text, or release notes based on git tags.
changelog-generator
Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.
shipping-methodology
Use when running claudikins-kernel:ship, preparing PRs, writing changelogs, deciding merge strategy, or handling CI failures — enforces GRFP-style iterative approval, code integrity validation, and human-gated merges.
git-workflow
Enforces the release-branch Git model: scaffold feature branches, open PRs with review checks, cut releases with tags, and view workflow reference.