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/gzb1128/opencode-plugin/releasenpx skills add gzb1128/opencode-plugin --skill releasegit clone --depth 1 https://github.com/gzb1128/opencode-pluginWhat 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 | $0.00042 | $0.00619 |
| Opus 5 | $0.00021 | $0.00309 |
| Sonnet 5 | $0.00008 | $0.00124 |
| Haiku 4.5 | $0.00004 | $0.00062 |
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 yesterday.
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.
What it actually says
Release
项目使用 GitHub Actions + GoReleaser 自动构建发布。Agent 只需创建并推送 tag，CI 负责其余一切。
Workflow
-
确认工作区干净
git status --porcelain有未提交的变更则先处理，不要带着脏工作区发版。
-
确定版本号（遵循 SemVer）
git tag --sort=-v:refname | head -1 # 最新 tag git log <latest-tag>..HEAD --oneline # 新增 commits- 有新 feature → minor 版本 bump（如 v0.2.0 → v0.3.0）
- 只有 bugfix → patch bump（如 v0.2.0 → v0.2.1）
- 重大变更 → major bump
-
创建并推送 tag
git tag -a v0.3.0 -m "v0.3.0" git push origin v0.3.0 -
监控 CI
gh run list --workflow=release.yml --limit 3CI 会自动：运行测试 → GoReleaser 构建多平台二进制 → 创建 GitHub Release 并上传 artifacts + checksums。
禁忌
- 禁止本地运行
goreleaser release— 会上传 assets 到 GitHub，导致 CI 因 assets 冲突失败 - tag 必须打在 HEAD commit 上 — 否则 goreleaser 会报
tag was not made against commit校验失败
故障排查
tag 打错了位置
git tag -d v0.3.0
git push origin :refs/tags/v0.3.0
git tag -a v0.3.0 -m "v0.3.0"
git push origin v0.3.0
CI 因已有 release 失败
本地 goreleaser 提前创建了 release 导致冲突时：
gh release delete v0.3.0 --yes --cleanup-tag
git tag -a v0.3.0 -m "v0.3.0"
git push origin v0.3.0
查看 CI 日志
gh run view <run-id> --log-failed # 查看失败日志
gh run watch <run-id> --exit-status # 实时跟踪
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.
- yesterday First seen · 71 lines · 42 tokens per session scan A ae3f4299d50f
release is a skill published in the GitHub repository gzb1128/opencode-plugin (1 stars, last pushed 2mo ago), licensed MIT. It adds 42 tokens to every session and 619 once invoked, about $0.0002 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
new
Use when user asks to create a release, cut a release, or publish a version. Auto-detects GitHub vs GitLab vs Gitea, calculates semantic version, generates release notes from PRs/MRs or commits, shows preview for confirmation before publishing.
writing-style
Use for technical communication - GitHub/GitLab tickets, PR/MR descriptions, issue comments, code review comments, commit messages. Direct, brief style with no AI-speak. NOT for README.md, public docs, or blog posts.
root-cause-investigator
Systematic root cause analysis for errors, bugs, and unexpected behaviors using 5-Why methodology. Use when user reports errors, build failures, test failures, performance issues, integration problems, or any "it's not working" scenarios.
ai-slop-reviewer
AI가 생성한 텍스트에서 기계적 패턴(AI 슬롭)을 감지하고 인간적인 글쓰기로 수정하는 스킬. 모든 텍스트 산출물(블로그, 뉴스레터, 카피, 사업계획서, 계약서, 제안서, 보고서, 이메일, 랜딩 카피 등)의 필수 후처리 단계로 사용합니다. 다음과 같은 요청 시 반드시 이 스킬을 사용하세요: "AI 티 나는 부분 고쳐줘", "사람이 쓴 것처럼 수정해줘", "AI 슬롭 제거해줘" "너무 AI 같아", "너무 딱딱해", "자연스럽게 다듬어줘" "이 글 AI가 쓴 것 같아 보여서...", "어색한 표현 수정해줘" "보고서가 너무 기계적이야", "이메일이 너무 형식적이야"…
finance-investor-relations
투자 유치를 위한 IR 피치덱과 3개년 재무 모델(매출 예측·손익·현금흐름·밸류에이션)을 만들어 드립니다. 다음과 같은 요청 시 사용하세요: "IR 덱 만들어줘" "투자자 피치 자료 써줘" "재무 모델 만들어줘" "매출 예측 좀 해줘" "밸류에이션 계산해줘" "시리즈 A 투자 유치 자료 준비해줘" "투자자 보고서 정리해줘" 투자 단계(Pre-SeedSeries B)에 맞춘 12슬라이드 피치덱·재무 모델·예상 질문 Q&A를 만들고, PPT/엑셀 변환으로 이어집니다.
career-portfolio
한국 신입 취준생·재직자를 위한 분야별 포트폴리오 구성과 프로젝트 기술서 작성 스킬입니다. "포트폴리오 만들어줘", "프로젝트 정리해줘", "노션 포트폴리오 1시간 만에"처럼 말하면 됩니다. 개발(GitHub·기술 블로그)/디자인(Figma·Behance)/마케팅/기획 분야별 + 검색되는 노션 포트폴리오 + 채용공고 맞춤형 1page 셀링 + 877건 노하우 기반 비중 배분을 지원합니다.