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 skills add b3rys/b3rys-team-os --skill b3os-release-opsgit clone --depth 1 https://github.com/b3rys/b3rys-team-osWrote 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/b3rys/b3rys-team-os/b3os-release-ops)<a href="https://agentmods.dev/skills/b3rys/b3rys-team-os/b3os-release-ops"><img src="https://agentmods.dev/badge/skills/b3rys/b3rys-team-os/b3os-release-ops/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/b3rys/b3rys-team-os/b3os-release-ops"><img src="https://agentmods.dev/badge/skills/b3rys/b3rys-team-os/b3os-release-ops.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 66 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 71 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00113 | $0.01505 |
| Opus 5 | $0.00056 | $0.00753 |
| Sonnet 5 | $0.00023 | $0.00301 |
| Haiku 4.5 | $0.00011 | $0.00151 |
Grade A, and why
b3os-release-ops 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 10d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
b3os-release-ops — 공개 배포·머지·핫픽스 게이트
정본 문서: docs/DEPLOY_MERGE_HOTFIX_WORKFLOW.md
언제 invoke하나
- b3os 공개
main에 PR을 merge하기 전. - live deploy(라이브 배포)하기 전/후.
- hotfix(긴급 수정)를 만들거나 머지할 때.
- force-push/history rewrite/orphan public snapshot 같은 공개 기록 재작성 논의가 있을 때.
- 봇이 “자동 머지해도 되는가?”를 판단해야 할 때.
빠른 판정
| 작업 | 봇 자율 가능? | 필수 게이트 |
|---|---|---|
| 문서 오탈자, 링크, 포맷팅 | 가능 | clean worktree, preflight, 가능하면 리뷰 |
| 테스트만 수정, 제품 동작 불변 | 제한적 가능 | 관련 테스트, preflight, 리뷰 1명 |
| 코드 동작 변경 | 불가 | PR, CI/typecheck, member review, 필요 시 harness |
| DB·권한·보안·시크릿 | 불가 | GD 승인, 리뷰, rollback, 감사 로그 |
| live deploy/restart | 불가 | GD/운영 승인, dry-run, build, acceptance, rollback |
| branch protection/force-push | 불가 | GD 승인, 2명 또는 harness review, backup, audit |
표준 실행 절차
1. PR merge 전
# 작업 브랜치에서
skills/b3os-release-ops/scripts/release-preflight.sh --mode merge
bun run typecheck # 코드 변경일 때
확인:
git status가 clean인지.- 브랜치가
main이 아닌지. origin/main..HEADcommit author·committer email이 GitHub noreply인지.- GitHub
mainbranch protection이 켜져 있는지. - PR 리뷰 1명 이상을 받았는지.
2. clean merge
- 공개 기록에 남길 author가 GD라면
gd.onnoreply email로 재작성한다. - merge 수행 계정은 GitHub Settings → Emails에서 “Keep my email addresses private”를 먼저 켠다. GitHub 웹/squash merge commit은 브랜치 commit이 all-noreply여도 머지 수행 계정의 author·committer email을 남길 수 있다.
- rebase/amend/fast-forward merge도 committer email이 로컬 실명 email로 남을 수 있으므로 author와 committer를 모두 확인한다.
- squash/rebase는 PR 범위 안에서만 한다.
- branch protection을 우회하거나 완화하지 않는다.
- merge 후
git fetch origin main을 실행하고skills/b3os-release-ops/scripts/release-preflight.sh --mode post-merge로origin/maintip author·committer email이 모두 noreply인지 확인한다. - post-merge 검증 뒤
main을 fast-forward로 맞춘다.
3. live deploy
git fetch origin main
git --no-pager log --oneline HEAD..origin/main # 반영될 commit 확인(dry-run)
skills/b3os-release-ops/scripts/release-preflight.sh --mode deploy --live-dir "$PWD"
PREV="$(git rev-parse HEAD)" # 롤백 지점 — 보고에 남긴다
git reset --hard origin/main
bun install && bun run build
bun run service restart # 상시가동 미등록이면 `bun run start` 재기동
What ships with it
6 files 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.
- 10d ago First seen · 139 lines · 113 tokens per session scan A 078e4c3dd430
b3os-release-ops is a skill published in the GitHub repository b3rys/b3rys-team-os (13 stars, last pushed yesterday), licensed Apache-2.0. It adds 113 tokens to every session and 1,505 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
release-gate-loop
A release check that tests a change, reports whether it passes, and can run a limited fix-and-retest cycle. A release is the act of making a software version available.
agent-framework-py-release
Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
gh-credit-harvest
Harvest one community PR into a release branch with authorship and credit preserved, verified green, and a warm thank-you.
release
Skill "release" from Hmbown/Codewhale, covering release, invocation, non-goals and workflow.
git-integration
Git commit patterns, formats, and conventions for GSD methodology. Provides atomic commits per task, structured commit messages, planning file commits, branch management, and milestone tag operations.