Borrowing it
Nothing to install: this file belongs to ggwhite/4x. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ggwhite/4x/main/.claude/skills/release/SKILL.mdgit clone --depth 1 https://github.com/ggwhite/4xWrote 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/ggwhite/4x/release)<a href="https://agentmods.dev/skills/ggwhite/4x/release"><img src="https://agentmods.dev/badge/skills/ggwhite/4x/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.
<a href="https://agentmods.dev/skills/ggwhite/4x/release"><img src="https://agentmods.dev/badge/skills/ggwhite/4x/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00066 | $0.01029 |
| Opus 5.5 | $0.00026 | $0.00412 |
| Sonnet 5.5 | $0.00013 | $0.00206 |
| Haiku 4.5 | $0.00007 | $0.00103 |
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.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release
Publish a new 4x version. The CI pipeline (goreleaser + homebrew) triggers on tag push, so the job here is: write accurate release notes, get user approval, then tag and push.
Workflow
1. Determine version
git tag -l 'v*' --sort=-v:refname | head -1
Bump the patch number by default (e.g., v0.1.8 -> v0.1.9). If the user specifies minor or major, bump accordingly.
Show the user: "上個版本是 vX.Y.Z，這次準備發 vA.B.C" and confirm before continuing.
2. Collect changes
git log <last-tag>..HEAD --oneline --no-decorate
If there are zero commits since the last tag, stop and tell the user there's nothing to release.
3. Draft changelog section
Read the existing CHANGELOG.md to match its style. The format follows Keep a Changelog:
## [X.Y.Z] - YYYY-MM-DD
### Fixes
- **Short name** — description of the fix
### Features
- **Short name** — description of the feature
Categorization rules:
fix/bugfixcommits ->### Fixesfeat/ feature commits ->### Featuresci/ workflow commits ->### CIdocscommits ->### Docs(only if user-facing; skip changelog-only docs commits)refactor/perf/chore->### Internal(only if noteworthy; skip trivial ones)
Each item should be a concise, user-facing description — not a raw commit message. Rewrite commit messages into the bold-name-em-dash style. Group related commits into a single item when they address the same thing.
Skip commits that are only changelog/release housekeeping (e.g., "docs: vX.Y.Z changelog").
4. Preview
Show the drafted changelog section to the user in full. Ask: "這樣 OK 嗎？要調整什麼？"
Proceed only after the user approves; if they request changes, revise and show again.
5. Update CHANGELOG.md
Insert the new version section at the top, right after the file header (the "# Changelog" heading and the format description paragraph). Leave existing sections untouched (see Important Rules).
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.
- 1mo ago First seen · 128 lines · 66 tokens per session scan A 38c274c549d0
release is a skill published in the GitHub repository ggwhite/4x (34 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 1,029 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
github
Skill "github" from Hmbown/Codewhale, covering github, when to use, setup, workflow and non-goals.
git-iris
Use this skill when generating commit messages, pull request descriptions, release notes, changelogs, or code reviews in a repository where git-iris is available. Activates on requests like "commit this", "write a commit message", "draft a PR", "generate release notes", "write a changelog", or "review my changes" when…
shipping-and-launch
Prepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.
push-handoff
Commit and push a verified handoff plus its artifacts, only under explicit authority, and prove the push happened by reading the remote SHA back. Use as the final delivery step after artifacts are ready, when the user asks to push work, or when a handoff needs to reach the remote. Refuses to claim success without…
land
Drive open PRs to merged — re-establish each PR's real state, resolve review threads, conflicts, failing checks, and CI failures under a bounded repair budget, land only the contiguous verified run bottom-up through the project's forge, watch until the checks pass and each merge lands, and stop at the ceiling. Use…
otito-review
Run otito review and gate before merge — composite verdict, PR context, and PASS/WARN/FAIL checks. Invoke before declaring a PR merge-ready.