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-supports-opsgit 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-supports-ops)<a href="https://agentmods.dev/skills/starcat-app/starcat/starcat-supports-ops"><img src="https://agentmods.dev/badge/skills/starcat-app/starcat/starcat-supports-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/starcat-app/starcat/starcat-supports-ops"><img src="https://agentmods.dev/badge/skills/starcat-app/starcat/starcat-supports-ops.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 | $0.00097 | $0.00970 |
| Opus 5.5 | $0.00039 | $0.00388 |
| Sonnet 5.5 | $0.00019 | $0.00194 |
| Haiku 4.5 | $0.00010 | $0.00097 |
Grade A, and why
starcat-supports-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 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Starcat Supports 后端运维
使用这个 skill 处理 supports/ 下自建后端 API 的本地联调和 Fly.io 运维。所有说明必须使用中文；命令、路径、环境变量、服务名等技术字面量保持原文。
硬性规则
- 先说明操作计划和副作用，等 dong4j 明确确认后再执行会改变外部状态的命令。
- 对生产 Fly.io 操作默认先只读检查：
make fly-status-all、make fly-health-all、fly secrets list。 - 不要打印
.env或 Fly secrets 明文；涉及 key 的命令只报告变量名和同步结果。 fly-restore-*、fly-wipe-data-*、fly secrets set、fly deploy都是高风险操作，必须单独确认。- 保留无关 dirty files；本地服务启动/停止不应修改 Swift 代码或文档。
入口选择
| 任务 | 推荐入口 |
|---|---|
| 启动全部本地 Go API | make start-supports 或 cd supports && ./start-all.sh |
| 停止全部本地 Go API | make stop-supports 或 cd supports && ./start-all.sh --stop |
| 查看本地服务状态 | cd supports && ./start-all.sh --status |
| 同步全部 Fly secrets | make sync-fly-secrets 或 make -C supports fly-secrets-all |
| 查看 Fly 状态/健康 | make -C supports fly-status-all / make -C supports fly-health-all |
| 备份 Fly /data | make -C supports fly-backup-<service> |
| 恢复 Fly /data | make -C supports fly-restore-<service> LOCAL_DB=... 或 RESTORE_ARCHIVE=... |
| 生成 API key | bash supports/scripts/gen-api-key.sh [count] [--env] |
| 预热 wiki 缓存 | bash supports/scripts/warm-wiki-cache.sh --dry-run 后再决定是否真实预热 |
把 supports .env key 写入客户端编译配置 |
make setup-production-api-keys |
标准工作流
- 读取
references/ops-map.md，确认目标服务、命令和风险等级。 - 先做只读检查：
git status --shortmake -C supports fly-health-all或本地./start-all.sh --status- 对 secrets 只用
fly secrets list -a <app>，不要读取或输出值。
- 说明命令会影响本地进程、Fly secrets、Fly /data、还是客户端配置。
- 等确认后执行。
- 执行后验证：
- 本地服务：
./start-all.sh --status和对应/healthz。 - Fly secrets：
fly secrets list -a <app>。 - Fly 备份：检查
supports/backups/<app>/<timestamp>/data.tar.gz和MANIFEST.txt。 - Fly 恢复：查看
/data列表和/healthz。
- 本地服务：
重要提醒
supports/start-all.sh必须从supports/根启动，它会进入各项目根目录执行服务，不能从bin/目录直接运行服务。- 有状态服务是
sharing、trending、weekly、wiki、discovery；recommend没有持久化卷。 - Fly restore 会覆盖生产
/data，恢复前先建议备份。 sync-production-api-keys-from-env.sh会重写Configs/Secrets.xcconfig，这是仓库文件变更，不是只读运维。
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 · 58 lines · 97 tokens per session scan A d147c8dcc64b
starcat-supports-ops is a skill published in the GitHub repository starcat-app/Starcat (215 stars, last pushed yesterday), licensed MIT. It adds 97 tokens to every session and 970 once invoked, about $0.0004 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.
starcat-supports-ops compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| starcat-supports-opsstarcat-app/Starcat | Skill | 215 | yesterday | MIT | A | 97 | 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 |
| effect-patterns-making-http-requestsPaulJPhilp/EffectPatterns | Skill | 806 | 4mo ago | MIT | A | 30 | Claude Code |
| memobasemaximskorohod/memobase | Skill | 22 | 17d ago | MIT | A | 25 | Claude Code, Codex |
| effect-patterns-streams-sinksPaulJPhilp/EffectPatterns | Skill | 806 | 4mo ago | MIT | A | 29 | Claude Code |