菜单
Infrastructure cost and expiry monitor. Checks Netlify, Supabase, domains, SSL, and API-cost risk signals. Trigger when: /cost-check, cost monitoring, infrastructure costs, domeny, wygasanie, koszty.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | cost-check |
| description | Infrastructure cost and expiry monitor. Checks Netlify, Supabase, domains, SSL, and API-cost risk signals. Trigger when: /cost-check, cost monitoring, infrastructure costs, domeny, wygasanie, koszty. |
Report infrastructure cost, plan, quota, and expiry risks.
Configure for your project. Maintain the list of services below in
.claude/memory/reference_<provider>.md(or equivalent) and reference it from here.
| Service | Identifier |
|---|---|
| Hosting (e.g. Netlify/Vercel) primary | <SITE_NAME>, site ID <SITE_ID> |
| Hosting secondary (if any) | <SITE_NAME>, site ID <SITE_ID> |
| Database (e.g. Supabase/Postgres) | project ref / connection string |
| Domains | <DOMAIN_PRIMARY>, <DOMAIN_SECONDARY>, plus any domains in hosting |
Use Netlify MCP when available:
If MCP is unavailable, use Netlify CLI/API only if already authenticated. Do not request or print tokens.
test -f supabase/.temp/project-ref && cat supabase/.temp/project-ref
if command -v supabase >/dev/null 2>&1; then
supabase projects list
else
npx supabase projects list
fi
If Supabase CLI is not authenticated, report that billing/quota status was not checked.
Use the safest available command:
openssl s_client -servername <DOMAIN_PRIMARY> -connect <DOMAIN_PRIMARY>:443 </dev/null 2>/dev/null | openssl x509 -noout -dates
openssl s_client -servername <DOMAIN_SECONDARY> -connect <DOMAIN_SECONDARY>:443 </dev/null 2>/dev/null | openssl x509 -noout -dates
For registrar expiry, use whois if available:
whois <DOMAIN_PRIMARY>
whois <DOMAIN_SECONDARY>
If WHOIS is unavailable or redacted, say so and rely on Netlify/registrar data supplied by the user.
Look for AI/API usage points:
rg -n "OPENAI|ANTHROPIC|GEMINI|GOOGLE|AI_GATEWAY|generate-quiz|chat-with-ai|rate-limit" supabase src netlify .env.example
Report whether rate limiting exists before expensive calls. Look for guards such as rate-limit, throttle, quota, or model-strategy in your backend / serverless functions / API routes.
## Cost check
**Checked at:** YYYY-MM-DD HH:mm Europe/Warsaw
**Verdict:** ok / watch / action needed
### Alerts
| Severity | Service | Finding | Action |
|---|---|---|---|
### Netlify
- Primary: ...
- Secondary: ...
### Supabase
- Project: ...
- Plan/quota: checked / unavailable
### Domains and SSL
| Domain | DNS/SSL | Registrar expiry | Notes |
|---|---|---|---|
### API cost risk
- ...
action needed; within 60 days as watch.Shared multi-agent presence and claim protocol. Use before any coding agent starts work in this repo, when coordinating Claude/Codex/Gemini sessions, or when checking who is already working on the repository. Triggers: agent session start, check agent presence, agent coordination, who's working on repo.
Claude Code adapter for the shared agent-presence protocol (for Codex CLI use `.agent/skills/dispatch-watcher/SKILL.md`, for Gemini CLI use `.agent/skills/dispatch-watcher-gemini/SKILL.md`). Use on Claude session start to run pre-flight, claim Slack-dispatched issues (@claude #N), and emit lifecycle events. Triggers: Claude session start, /dispatch, /agent-presence, message addressed to @claude in the dispatch channel.
Gemini CLI adapter for the shared agent-presence protocol (for Claude Code use `.agent/skills/dispatch-watcher-claude/SKILL.md`, for Codex CLI use `.agent/skills/dispatch-watcher/SKILL.md`). Use on Gemini session start to run pre-flight, claim Slack-dispatched issues (@gemini #N), and emit lifecycle events. Triggers: Gemini session start, /dispatch, /agent-presence, message addressed to @gemini in the dispatch channel.
Optional agent dispatch watcher — Phase 1 walking skeleton, Codex-flavored. Use on agent session start when a Slack-style dispatch channel assigns GitHub issues to a model handle such as @codex. For Claude use `.agent/skills/dispatch-watcher-claude/SKILL.md`, for Gemini use `.agent/skills/dispatch-watcher-gemini/SKILL.md`, for the full multi-agent contract see `.agent/skills/agent-presence/SKILL.md`.
PR merge supervisor workflow. Use to merge a GitHub PR safely — resolve review threads correctly, check CI, run an optional repo supervisor, and do post-merge cleanup. Trigger when: /merge, merge PR, complete a PR, finalize a PR.
Use when generating operational reports, release notes, demo readiness checks, stakeholder updates, infrastructure cost/expiry checks, or bilingual changelogs. Triggers: /release-notes, /investor-report, /demo-check, /cost-check, changelog, release notes, stakeholder report, monthly metrics, demo readiness, before demo, infrastructure costs, cost monitoring, certificate expiry.