Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Show AGNTCY/SLIM/CASA integration status — whether upstream AGNTCY packages are installed, which transport (local vs SLIM) is active, and whether CASA enforcement is enabled. Use when the user asks "is AGNTCY configured?", "show SLIM/CASA status", or "is AGNTCY/IOC integration active?".
.claude/skills/ruvnet-agntcy-status/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 8% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -47% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -21% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -66% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -54% | 0% |
Scaffolding stub — not yet implemented. This skill will report, once ruflo-agntcy ships real logic (see ADR-380):
@claude-flow/agntcy (TS) and/or the Rust ruflo-agntcy crate are installed as optionalDependencies, or absent (the expected default today — no such upstream package exists yet publicly).allow/deny/budget_usd/expires_at currently in force (ADR-380 §3).hive-mind_broadcast/hive-mind_consensus.agent.identity, coordination.episode, authorization.decision, etc., ADR-380 §5) are being emitted through ruflo-observability.Until upstream AGNTCY/SLIM packages exist, this status check MUST report "not configured — see ADR-380" rather than fabricate a healthy status. No network call to AGNTCY infrastructure (Directory, SLIM broker) is safe to make from this skill until a real client library is available.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 8,477 | 5,484 | -35% | 1 | 1 | 0% | 1,259 | 1,354 | +8% | 0 | 0 | — |
case-02 | fail→pass | 13,039 | 4,118 | -68% | 1 | 1 | 0% | 2,070 | 1,105 | -47% | 0 | 0 | — |
case-03 | fail→pass | 10,785 | 5,663 | -47% | 1 | 1 | 0% | 1,697 | 1,344 | -21% | 0 | 0 | — |
case-04 | pass→pass | 9,336 | 3,264 | -65% | 1 | 1 | 0% | 1,447 | 851 | -41% | 0 | 0 | — |
case-05 | fail→pass | 12,846 | 2,210 | -83% | 1 | 1 | 0% | 2,015 | 688 | -66% | 0 | 0 | — |
case-06 | fail→pass | 10,739 | 2,376 | -78% | 1 | 1 | 0% | 1,586 | 732 | -54% | 0 | 0 | — |
case-07 | pass→pass | 9,535 | 1,950 | -80% | 1 | 1 | 0% | 1,424 | 623 | -56% | 0 | 0 | — |
case-08 | fail→pass | 13,400 | 2,311 | -83% | 1 | 1 | 0% | 2,122 | 613 | -71% | 0 | 0 | — |
case-09 | fail→pass | 7,523 | 2,672 | -64% | 1 | 1 | 0% | 1,271 | 765 | -40% | 0 | 0 | — |
case-10 | fail→pass | 10,300 | 2,240 | -78% | 1 | 1 | 0% | 1,770 | 666 | -62% | 0 | 0 | — |
case-11 | fail→pass | 12,741 | 1,974 | -85% | 1 | 1 | 0% | 2,097 | 636 | -70% | 0 | 0 | — |
case-12 | fail→pass | 11,958 | 8,638 | -28% | 1 | 1 | 0% | 1,671 | 1,021 | -39% | 0 | 0 | — |
case-13 | fail→pass | 6,986 | 2,221 | -68% | 1 | 1 | 0% | 1,040 | 625 | -40% | 0 | 0 | — |
case-14 | fail→pass | 6,777 | 1,434 | -79% | 1 | 1 | 0% | 1,075 | 554 | -48% | 0 | 0 | — |
case-15 | fail→pass | 7,428 | 2,091 | -72% | 1 | 1 | 0% | 1,223 | 676 | -45% | 0 | 0 | — |
case-16 | fail→pass | 12,828 | 3,811 | -70% | 1 | 1 | 0% | 1,843 | 1,059 | -43% | 0 | 0 | — |
case-17 | fail→pass | 13,155 | 2,354 | -82% | 1 | 1 | 0% | 1,630 | 747 | -54% | 0 | 0 | — |
case-18 | fail→pass | 8,009 | 1,294 | -84% | 1 | 1 | 0% | 1,215 | 541 | -55% | 0 | 0 | — |
case-19 | fail→pass | 9,822 | 3,661 | -63% | 1 | 1 | 0% | 1,648 | 1,057 | -36% | 0 | 0 | — |
case-20 | fail→pass | 9,828 | 1,934 | -80% | 1 | 1 | 0% | 1,421 | 641 | -55% | 0 | 0 | — |
case-21 | pass→pass | 13,104 | 3,768 | -71% | 1 | 1 | 0% | 1,898 | 874 | -54% | 0 | 0 | — |
case-22 | fail→pass | 12,289 | 2,358 | -81% | 1 | 1 | 0% | 1,817 | 732 | -60% | 0 | 0 | — |
case-23 | pass→pass | 28,007 | 13,544 | -52% | 1 | 1 | 0% | 2,926 | 3,134 | +7% | 0 | 0 | — |
case-24 | pass→pass | 7,550 | 6,097 | -19% | 1 | 1 | 0% | 1,425 | 1,501 | +5% | 0 | 0 | — |
case-25 | pass→pass | 2,984 | 3,057 | +2% | 1 | 1 | 0% | 388 | 825 | +113% | 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. 25 cases were attempted. The headline lift of +76 percentage points is the difference between those two pass rates over the 25 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.
Other measured skills in the registry, with their headline benchmark lift.