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 starcat-app/Starcat --skill starcat-backend-releasegit clone --depth 1 https://github.com/starcat-app/StarcatWrote 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/starcat-app/starcat/starcat-backend-release)<a href="https://agentmods.dev/skills/starcat-app/starcat/starcat-backend-release"><img src="https://agentmods.dev/badge/skills/starcat-app/starcat/starcat-backend-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/starcat-app/starcat/starcat-backend-release"><img src="https://agentmods.dev/badge/skills/starcat-app/starcat/starcat-backend-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 | $0.00083 | $0.00810 |
| Opus 5.5 | $0.00033 | $0.00324 |
| Sonnet 5.5 | $0.00017 | $0.00162 |
| Haiku 4.5 | $0.00008 | $0.00081 |
Grade A, and why
starcat-backend-release scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Fly:`fly status -a <app>` 和 `curl https://<app>.fly.dev/healthz` 正常。 What it actually says
Starcat 后端 API 发布
使用这个 skill 处理 supports/starcat-*-api 独立后端仓库的发布流程。它不同于主 App 的 starcat-release,也不同于日常 Fly 运维的 starcat-supports-ops。
硬性规则
- 先只读检查,再说明发布计划;等 dong4j 明确确认后才能执行
deploy.sh、git push、gh pr merge、git tag。 - 发布脚本会影响 GitHub PR、tag、GitHub Actions 和 Fly deploy,不要在未确认时运行。
- 默认不要删除远端 tag 或强推。
- 工作区必须干净;发现无关 dirty files 时停止并说明。
- 不要把主 App 的
scripts/release-direct.sh用到 supports 子项目。
入口选择
| 项目 | 发布入口 | 说明 |
|---|---|---|
| sharing/trending/weekly/wiki | supports/<project>/scripts/deploy.sh vX.Y.Z |
完整 PR -> merge -> tag -> Actions/Fly 流程 |
| recommend | supports/starcat-recommend-api/scripts/deploy.sh vX.Y.Z |
先跑 Go 测试/构建,再本地 tag + push tag |
| discovery | supports/starcat-discovery-api/scripts/deploy.sh vX.Y.Z |
直接 fly deploy -a starcat-discovery-api --build-arg VERSION=... |
如果用户没说明具体服务,先问服务名和目标版本号。版本必须是 vX.Y.Z。
标准工作流
- 读取
references/backend-release-map.md。 - 进入目标 supports 子项目目录。
- 只读检查:
git status --shortgit branch --show-currentgit tag --list 'v*' --sort=-v:refname | headgh auth status
- 先跑 dry-run,适用于 sharing/trending/weekly/wiki:
./scripts/deploy.sh --dry-run vX.Y.Z
- 说明脚本将创建 PR、合并、切 main、打 tag、push tag,并触发 CI/Fly。
- 等确认后执行真实发布。
- 发布后检查 GitHub Actions 和 Fly 状态。
关键约束
- sharing/trending/weekly/wiki 的 tag 必须在 PR merge 后创建,指向 main 的 merge commit。
- 不允许在 main/master 上运行共享 deploy 脚本。
- 不能用 squash merge,否则会丢失 dev 上多个 commit 信息。
- 推 tag 后必须等 Go workflow 成功,Fly deploy/release 才会继续。
- recommend/discovery 的脚本更简单,不等同于共享 deploy 流程,使用前必须先读脚本。
验证
- GitHub:PR 已合并,tag 存在且指向 main 期望 commit。
- Actions:Go workflow 通过,后续 Fly deploy/release 按预期触发。
- Fly:
fly status -a <app>和curl https://<app>.fly.dev/healthz正常。
参考
详细项目差异、命令和失败恢复见 references/backend-release-map.md。
What ships with it
2 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.
- 2mo ago First seen · 60 lines · 83 tokens per session scan A 0ebc8725cc26
starcat-backend-release is a skill published in the GitHub repository starcat-app/Starcat (215 stars, last pushed yesterday), licensed MIT. It adds 83 tokens to every session and 810 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
starcat-backend-release compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| starcat-backend-releasestarcat-app/Starcat | Skill | 215 | yesterday | MIT | A | 83 | Codex |
| scope-creep-detectorShubhamsaboo/awesome-llm-apps | Skill | 144k | yesterday | Apache-2.0 | A | 98 | Claude Code, Codex |
| mem0-test-integrationmem0ai/mem0 | Skill | 68k | 2d ago | Apache-2.0 | A | 207 | Claude Code, Codex |
| wegent-knowledgewecode-ai/Wegent | Skill | 882 | yesterday | Apache-2.0 | A | 60 | Claude Code, Codex |
| binder-appmpazik/Binder | Skill | 40 | 17d ago | MIT | A | 74 | Claude Code, Codex |
| my-wikiNimaChu/my-wiki | Skill | 127 | 22d ago | MIT | A | 51 | Codex |
| memobasemaximskorohod/memobase | Skill | 22 | 17d ago | MIT | A | 25 | Claude Code, Codex |