Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Single-shot programmatic dump of all cost data — total spend, per-tier, top session, budget status, federation aggregate. JSON or markdown.
.claude/skills/ruvnet-cost-summary/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -40% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -38% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -32% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -59% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -34% | 0% |
A stable single-call interface that other plugins / scripts / dashboards can shell out to and parse. ADR-0002 considered exposing cost_report / cost_summary as proper MCP tools but deferred that — adding MCP tools requires modifying @claude-flow/cli source, out of scope for plugin-local work. This script is the equivalent: same data, exposed via a stdout JSON contract.
summary.mjs --format json and parses.json{ "exportedAt": "<ISO>", "total_cost_usd": 1546.36, "sessionCount": 1, "conversationCount": 1, "byTier": { "haiku": 0, "sonnet": 0, "opus": 1546.36, "unknown": 0 }, "byModel": { "claude-opus-4-7": { "tier": "opus", "cost_usd": 1546.36, "messages": 1597, "input_tokens": 3090, "output_tokens": 3295940, "cache_creation_input_tokens": 10659599, "cache_read_input_tokens": 732833690 } }, "topSession": { "sessionId": "1dba3b8c-...", "total_cost_usd": 1546.36, "messageCount": 1597 }, "budget": { "budget_usd": 2500.00, "setAt": "<ISO>", "spent_usd": 1546.36, "utilization": 0.6185, "level": "INFO" }, "federation": { "eventCount": 0, "peerCount": 0, "totalUsd24h": 0 } }
bash# Markdown (default) node plugins/ruflo-cost-tracker/scripts/summary.mjs # JSON for programmatic consumption node plugins/ruflo-cost-tracker/scripts/summary.mjs --format json
Optional env: SUMMARY_NAMESPACE=cost-tracking, SUMMARY_FED_NAMESPACE=federation-spend, SUMMARY_FORMAT=json.
cost-report — narrative report (per-agent / per-model lens; uses same data)cost-export — pushes to Prometheus / webhook (this skill is pull-style; export is push-style)| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 12,251 | 4,849 | -60% | 1 | 1 | 0% | 3,072 | 1,856 | -40% | 0 | 0 | — |
case-16 | pass→pass | 8,889 | 5,987 | -33% | 1 | 1 | 0% | 1,725 | 1,105 | -36% | 0 | 0 | — |
case-02 | fail→fail | 4,067 | 2,941 | -28% | 1 | 1 | 0% | 743 | 1,100 | +48% | 0 | 0 | — |
case-03 | fail→pass | 12,777 | 4,412 | -65% | 1 | 1 | 0% | 2,620 | 1,627 | -38% | 0 | 0 | — |
case-04 | fail→pass | 11,620 | 3,761 | -68% | 1 | 1 | 0% | 1,901 | 1,287 | -32% | 0 | 0 | — |
case-05 | pass→pass | 17,181 | 1,682 | -90% | 1 | 1 | 0% | 1,216 | 977 | -20% | 0 | 0 | — |
case-22 | fail→fail | 23,029 | 21,708 | -6% | 1 | 1 | 0% | 3,802 | 4,791 | +26% | 0 | 0 | — |
case-06 | pass→pass | 10,609 | 1,326 | -88% | 1 | 1 | 0% | 1,781 | 896 | -50% | 0 | 0 | — |
case-07 | fail→pass | 12,223 | 1,472 | -88% | 1 | 1 | 0% | 2,308 | 947 | -59% | 0 | 0 | — |
case-08 | fail→pass | 7,880 | 3,188 | -60% | 1 | 1 | 0% | 1,416 | 941 | -34% | 0 | 0 | — |
case-09 | fail→pass | 7,411 | 2,343 | -68% | 1 | 1 | 0% | 1,279 | 1,092 | -15% | 0 | 0 | — |
case-10 | pass→pass | 9,274 | 1,847 | -80% | 1 | 1 | 0% | 1,799 | 1,093 | -39% | 0 | 0 | — |
case-11 | pass→pass | 5,820 | 6,078 | +4% | 1 | 1 | 0% | 1,092 | 1,149 | +5% | 0 | 0 | — |
case-12 | fail→pass | 7,664 | 1,316 | -83% | 1 | 1 | 0% | 1,301 | 978 | -25% | 0 | 0 | — |
case-13 | pass→pass | 5,845 | 2,368 | -59% | 1 | 1 | 0% | 977 | 1,149 | +18% | 0 | 0 | — |
case-14 | fail→pass | 11,770 | 1,284 | -89% | 1 | 1 | 0% | 2,192 | 915 | -58% | 0 | 0 | — |
case-15 | fail→pass | 11,785 | 2,765 | -77% | 1 | 1 | 0% | 2,227 | 1,255 | -44% | 0 | 0 | — |
case-17 | pass→pass | 6,671 | 4,507 | -32% | 1 | 1 | 0% | 1,079 | 959 | -11% | 0 | 0 | — |
case-18 | pass→pass | 9,267 | 1,076 | -88% | 1 | 1 | 0% | 1,714 | 898 | -48% | 0 | 0 | — |
case-19 | pass→pass | 3,579 | 1,055 | -71% | 1 | 1 | 0% | 607 | 881 | +45% | 0 | 0 | — |
case-20 | fail→pass | 10,294 | 4,846 | -53% | 1 | 1 | 0% | 1,710 | 1,634 | -4% | 0 | 0 | — |
case-21 | fail→fail | 13,453 | 14,421 | +7% | 1 | 1 | 0% | 2,741 | 3,778 | +38% | 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. 22 cases were attempted. The headline lift of +45 percentage points is the difference between those two pass rates over the 22 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.