Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Monitor provider health, circuit-breaker states, p50/p95/p99 latency metrics, and budget guard alerts. Inspect connection cooldowns and model lockouts in real time.
.claude/skills/diegosouzapw-omni-resilience/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 78% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 85% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 31% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -15% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 24% | 0% |
<!-- generated by src/lib/agentSkills/generator.ts; manual edits will be overwritten -->
Monitor provider health, circuit-breaker states, p50/p95/p99 latency metrics, and budget guard alerts. Inspect connection cooldowns and model lockouts in real time.
All requests require a valid Bearer token or session cookie. Obtain a token via POST /api/auth/login or configure REQUIRE_API_KEY=false for local development.
System health check
Returns system health including uptime, memory, circuit breakers, rate limits
bashcurl https://localhost:20128/api/monitoring/health \ -H "Authorization: Bearer $OMNIROUTE_TOKEN"
Get compression result-memo statistics
In-process compression result-memo observability snapshot — size, capacity, lifetime hits/misses/hitRate plus 1m/5m/15m/1h windowed rates. Lightweight (no DB, no provider reads) companion to GET /api/monitoring/health intended for frequent polling. Sent with Cache-Control: no-store, no-cache, must-revalidate. Counters reset on process restart.
bashcurl https://localhost:20128/api/monitoring/compression \ -H "Authorization: Bearer $OMNIROUTE_TOKEN"
GET provider metrics
bashcurl https://localhost:20128/api/provider-metrics \ -H "Authorization: Bearer $OMNIROUTE_TOKEN"
See the full OpenAPI specification at GET /api/openapi/spec or docs/openapi.yaml for detailed request/response schemas.
<!-- skill:custom-start --> <!-- Migrated from skills/omniroute-monitoring/SKILL.md (preserved curated content) -->
Requires OMNIROUTE_URL and OMNIROUTE_KEY. See entry-point SKILL for setup.
bashcurl $OMNIROUTE_URL/api/health \ -H "Authorization: Bearer $OMNIROUTE_KEY"
Returns: uptime, memory, active connections, circuit breaker states, rate limit status, cache stats.
Unauthenticated quick check:
bashcurl $OMNIROUTE_URL/api/health # → {"ok":true}
Circuit breakers prevent traffic from hitting failing providers.
States: CLOSED (normal), OPEN (blocked), HALF_OPEN (probe mode — auto-recovers).
bashcurl $OMNIROUTE_URL/api/monitoring/health \ -H "Authorization: Bearer $OMNIROUTE_KEY"
Response includes circuitBreakers array with per-provider state and resetAt timestamp.
bashcurl $OMNIROUTE_URL/api/providers/metrics \ -H "Authorization: Bearer $OMNIROUTE_KEY"
Response shape per provider:
json{ "provider": "anthropic", "requests": 1247, "successRate": 0.994, "latency": { "p50": 820, "p95": 2100, "p99": 3800 }, "circuitState": "CLOSED", "tokensUsed": 2847000 }
omniroute_get_health → full system health snapshot
omniroute_get_provider_metrics → p50/p95/p99 + circuit state per provider
omniroute_get_session_snapshot → cost, tokens, errors for current session
omniroute_check_quota → quota balance + percent remaining + reset time
omniroute_db_health_check → diagnose + auto-repair database driftbashcurl $OMNIROUTE_URL/api/quota \ -H "Authorization: Bearer $OMNIROUTE_KEY"
Returns used/total tokens and requests per provider/account, with resetAt timestamps.
Set a session spending limit that degrades or blocks requests when hit:
bashcurl -X POST $OMNIROUTE_URL/api/budget/guard \ -H "Authorization: Bearer $OMNIROUTE_KEY" \ -H "Content-Type: application/json" \ -d '{ "limitUsd": 5.00, "action": "degrade", "degradeTo": "openai/gpt-4o-mini" }'
action options:
degrade — switch to a cheaper model when limit is hitblock — return 429 when limit is hitalert — continue but add X-Budget-Warning headerOmniRoute logs every MCP tool call to mcp_audit table. Query via API:
bashcurl "$OMNIROUTE_URL/api/mcp/status" \ -H "Authorization: Bearer $OMNIROUTE_KEY"
Returns: server status, heartbeat, recent audit activity summary.
503 on health endpoint → OmniRoute is starting up; retry in 5sOPEN → provider is temporarily blocked; check resetAt to know when it auto-recovers429 budget_exceeded → budget guard limit reached; raise limit or wait for reset<!-- skill:custom-end -->
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 17,583 | 21,613 | +23% | 1 | 1 | 0% | 2,113 | 3,762 | +78% | 0 | 0 | — |
case-02 | fail→pass | 12,613 | 10,483 | -17% | 1 | 1 | 0% | 1,251 | 2,314 | +85% | 0 | 0 | — |
case-03 | fail→pass | 16,622 | 11,890 | -28% | 1 | 1 | 0% | 2,083 | 2,729 | +31% | 0 | 0 | — |
case-04 | fail→pass | 19,929 | 8,262 | -59% | 1 | 1 | 0% | 2,383 | 2,019 | -15% | 0 | 0 | — |
case-05 | fail→pass | 13,544 | 7,163 | -47% | 1 | 1 | 0% | 1,420 | 1,754 | +24% | 0 | 0 | — |
case-06 | fail→pass | 21,100 | 9,884 | -53% | 1 | 1 | 0% | 2,065 | 2,139 | +4% | 0 | 0 | — |
case-07 | fail→pass | 13,875 | 7,682 | -45% | 1 | 1 | 0% | 1,403 | 1,834 | +31% | 0 | 0 | — |
case-08 | pass→pass | 15,802 | 8,051 | -49% | 1 | 1 | 0% | 1,702 | 1,878 | +10% | 0 | 0 | — |
case-09 | fail→pass | 16,732 | 10,371 | -38% | 1 | 1 | 0% | 2,187 | 2,200 | +1% | 0 | 0 | — |
case-10 | fail→pass | 13,234 | 9,195 | -31% | 1 | 1 | 0% | 1,611 | 2,050 | +27% | 0 | 0 | — |
case-11 | fail→pass | 14,798 | 7,303 | -51% | 1 | 1 | 0% | 1,542 | 1,736 | +13% | 0 | 0 | — |
case-12 | pass→pass | 15,832 | 7,843 | -50% | 1 | 1 | 0% | 1,884 | 1,770 | -6% | 0 | 0 | — |
case-13 | fail→pass | 11,385 | 7,509 | -34% | 1 | 1 | 0% | 2,016 | 1,635 | -19% | 0 | 0 | — |
case-14 | fail→pass | 14,443 | 7,087 | -51% | 1 | 1 | 0% | 1,349 | 1,742 | +29% | 0 | 0 | — |
case-15 | fail→pass | 21,146 | 6,998 | -67% | 1 | 1 | 0% | 2,515 | 1,732 | -31% | 0 | 0 | — |
case-16 | fail→pass | 17,857 | 9,783 | -45% | 1 | 1 | 0% | 1,927 | 1,881 | -2% | 0 | 0 | — |
case-17 | fail→pass | 12,304 | 7,413 | -40% | 1 | 1 | 0% | 1,929 | 1,741 | -10% | 0 | 0 | — |
case-18 | fail→pass | 17,408 | 8,789 | -50% | 1 | 1 | 0% | 2,342 | 2,186 | -7% | 0 | 0 | — |
case-19 | pass→pass | 10,358 | 8,334 | -20% | 1 | 1 | 0% | 752 | 1,672 | +122% | 0 | 0 | — |
case-20 | pass→pass | 21,792 | 12,404 | -43% | 1 | 1 | 0% | 2,919 | 3,787 | +30% | 0 | 0 | — |
case-21 | pass→pass | 22,720 | 17,047 | -25% | 1 | 1 | 0% | 2,862 | 3,549 | +24% | 0 | 0 | — |
case-22 | pass→pass | 17,610 | 17,288 | -2% | 1 | 1 | 0% | 2,229 | 3,646 | +64% | 0 | 0 | — |
case-23 | pass→pass | 12,979 | 11,428 | -12% | 1 | 1 | 0% | 1,458 | 2,469 | +69% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted. The headline lift of +70 percentage points is the difference between those two pass rates over the 23 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 8/7/2026 | +77% |
Other measured skills in the registry, with their headline benchmark lift.