htop for your agentic-AI quota plans. Tracks remaining quota across AI coding subscriptions (Claude, Codex, Antigravity, Grok) and local runtimes, and routes the next request to whichever has budget. Local-first, cross-platform, zero usage tokens. CLI, desktop widget, MCP, LiteLLM.
- capability exposure inferred + 16
- recent drift inferred + 20
- tool safety inferred + 12
- trust mitigators mixed − 3
inferred mixed
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
graded 3m ago · see ecosystem CVEs →
- C · 41 → C · 45
- B · 21 → C · 41
- B · 24 → B · 21
No known CVEs for this server.
- high dangerous code
committed secret: Google OAuth client secret
analyzed commit bc6db2f · analyzer v28 · 2d ago
skills & prompt files 2
- agent-rules blisspixel-quotabot-bc6db2f/AGENTS.md
- agent-rules blisspixel-quotabot-bc6db2f/CLAUDE.md
danger signals2
- committed secret Google OAuth client secret blisspixel-quotabot-bc6db2f/collector/lib/adapters/antigravity.dart :150
GOCSPX…(35 chars, redacted) - committed secret Google OAuth client secret blisspixel-quotabot-bc6db2f/collector/lib/auth/google_auth.dart :31
GOCSPX…(35 chars, redacted)
- recent drift +20 capability drift →
[](https://mcpobservatory.com/servers/github:blisspixel/quotabot/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of blisspixel.