Borrowing it
Nothing to install: this file belongs to CIrcui-try/Circuit. 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/CIrcui-try/Circuit/main/.claude/commands/release.mdgit clone --depth 1 https://github.com/CIrcui-try/CircuitWrote 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/commands/circui-try/circuit/release)<a href="https://agentmods.dev/commands/circui-try/circuit/release"><img src="https://agentmods.dev/badge/commands/circui-try/circuit/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/commands/circui-try/circuit/release"><img src="https://agentmods.dev/badge/commands/circui-try/circuit/release.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00018 | $0.01941 |
| Opus 5.5 | $0.00007 | $0.00776 |
| Sonnet 5.5 | $0.00004 | $0.00388 |
| Haiku 4.5 | $0.00002 | $0.00194 |
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 2mo 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
develop의 변경사항을 모아 release/x.y.z 브랜치를 만들고 main으로 향하는 릴리즈 PR을 자동 생성한다.
$ARGUMENTS로 버전을 반드시 명시해야 한다 (예: /release 0.2.1). 비어 있거나 x.y.z 형식이 아니면 즉시 중단한다.
기존 PR 본문 구조 ground truth: PR #50 (gh pr view 50). 실제 PR 제목과 본문은 영어로 작성한다.
절차
1단계: 사전 확인
- 버전 인자 확인:
$ARGUMENTS가 비어 있거나x.y.z정규식 (^\d+\.\d+\.\d+$) 에 맞지 않으면 사용자에게 "버전을/release 0.2.1형식으로 명시해 주세요" 라고 알리고 즉시 중단. - 레포 루트 확인:
git rev-parse --show-toplevel이Reserviano루트인지 확인. - 변경사항 확인:
git status --porcelain결과가 비어 있어야 한다. uncommitted 변경이 있으면 알리고 중단 (release 작업에 의도치 않게 묶일 위험). - 원격 최신화:
git fetch origin main develop --tags. - 릴리즈 대상 존재 확인:
git rev-list --count origin/main..origin/develop이 0이면 "릴리즈할 변경사항 없음"으로 종료. - release 브랜치 충돌 확인:
git branch -a | grep release/로 진행 중인 release 브랜치가 있으면 사용자에게 알리고 진행 여부 확인. - 버전 중복 확인: 동일 버전의 태그(
v<버전>)나 release 브랜치(release/<버전>)가 이미 존재하면 알리고 중단.
2단계: 변경사항 수집
main..develop 범위의 머지된 PR 메타데이터를 수집한다. 본문 생성 소스로 쓰고, 커밋 메시지 prefix는 보조 신호다.
# 직전 release 시점 (main의 가장 최근 release PR merge 시각)
gh pr list --state merged --base main --search "release in:title" --limit 1 \
--json mergedAt,title,number
# 그 시점 이후 develop으로 머지된 PR 목록
gh pr list --state merged --base develop --search "merged:>=<직전 release merge 시각>" \
--json number,title,body,mergedAt
각 PR에서 추출:
- 제목의 conventional commit prefix (
feat,fix,refactor,perf,docs,chore,style,test,ci,build) - 본문 첫 단락의 영어 사용자 가치 설명 (
## Summary블록이 있으면 그 첫 줄). 원문이 한국어이면 영어로 번역해 사용한다.
카테고리 매핑:
feat:→ New featuresfix:→ Bug fixesrefactor:,perf:→ 사용자 가시 변경이면 본인 판단으로 New features 또는 Bug fixes 중 더 적합한 곳에, 아니면 제외docs:,chore:,style:,test:,ci:,build:→ 제외
3단계: 버전 확정
$ARGUMENTS로 받은 값을 그대로 사용한다.
4단계: PR 본문 자동 생성
PR #50 톤을 참고해 다음 템플릿으로 작성:
## <version>
### New features
- <English user-value summary extracted from feat PRs>
### Bug fixes
- <English problem-oriented summary extracted from fix PRs>
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.
- 2mo ago First seen · 169 lines · 0 tokens per session scan A 626831b55334
release is a command published in the GitHub repository CIrcui-try/Circuit (5 stars, last pushed 5mo ago), licensed MIT. It adds 18 tokens to every session and 1,941 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
release
Verify, write the CHANGELOG, cut a version — then hand the release sequence back.
release
Command "release" from voodootikigod/skills-check, covering arguments and steps.
ship
Run the pre-launch checklist via parallel fan-out to specialist personas, then synthesize a go/no-go decision.
CHANGELOG
Command "CHANGELOG" from bytedance/UI-TARS-desktop, covering 0.4.0 2024-12-10 - add logging, 1.2.29, 1.2.28, 1.2.26 and 1.2.25.
vios-release-note
Generate a complete VIOS multi-arch release note for a given build drop version. Fetches container images from GitLab compose.env, GitLab commit titles since the previous release tag, Jira VST tickets, NVBugs entries, Slack channel evidence, and Outlook email evidence, then renders and saves a formatted release note.
ship
A command that runs several specialist checks before software is released, then combines their findings into a decision about whether to launch.