Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generate a cost report showing token usage and USD costs by agent and model
.claude/skills/ruvnet-cost-report/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-08 | ✗→✓ | ▲ Improved | -37% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -7% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -33% | 0% |
| case-14 | ✗→✓ | ▲ Improved | -7% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 89% | 0% |
Generate a comprehensive cost report showing token usage, USD costs, and budget utilization for the specified period.
When you need to understand current spending -- how much each agent costs, which models consume the most budget, and whether you're on track to stay within budget.
mcp__plugin_ruflo-core_ruflo__memory_search (or _list / _retrieve) on the cost-tracking namespace for the specified period (default: today). The memory_* tools route by namespace string; the agentdb_hierarchical-* tools do not (they route by tier working|episodic|semantic), so don't use them here. See ruflo-agentdb ADR-0001 §"Namespace convention" for the routing contract.1a. Read measured booster data -- if docs/benchmarks/runs/latest.json exists, load it via Bash-shelled node -e 'console.log(JSON.stringify(JSON.parse(require("fs").readFileSync("docs/benchmarks/runs/latest.json")).summary))'. This provides Tier 1 measured values — booster cost/edit ($0), avg latency, win rate, plus any LLM baseline that was run (Gemini, Sonnet 4.6, Opus 4.7 latencies and per-edit costs). Use these in step 4 for the measured Tier breakdown rather than estimated.
[AGENT_BOOSTER_AVAILABLE] flag stored by the cost-booster-route skill in cost-tracking; (c) the model name as fallback (haiku → Tier 2; sonnet/opus → Tier 3). Sum costs per tier, compute share, and count Tier 1 bypasses. The tier breakdown is the most actionable single line — it tells the user what fraction of Sonnet/Opus spend was Tier 1-eligible.memory_retrieve and compute utilization percentage, check alert thresholds (50%/75%/90%/100%)bashnpx @claude-flow/cli@latest memory search --query "cost report for today" --namespace cost-tracking npx @claude-flow/cli@latest memory list --namespace cost-tracking
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-02 | fail→fail | 18,808 | 8,464 | -55% | 1 | 1 | 0% | 3,985 | 1,457 | -63% | 0 | 0 | — |
case-08 | fail→pass | 15,444 | 3,444 | -78% | 1 | 1 | 0% | 2,412 | 1,518 | -37% | 0 | 0 | — |
case-01 | fail→fail | 6,563 | 6,285 | -4% | 1 | 1 | 0% | 1,183 | 1,288 | +9% | 0 | 0 | — |
case-03 | fail→fail | 14,780 | 28,245 | +91% | 1 | 1 | 0% | 2,866 | 1,352 | -53% | 0 | 0 | — |
case-04 | pass→fail | 3,978 | 6,342 | +59% | 1 | 1 | 0% | 716 | 1,080 | +51% | 0 | 0 | — |
case-05 | pass→fail | 5,437 | 6,893 | +27% | 1 | 1 | 0% | 1,034 | 1,481 | +43% | 0 | 0 | — |
case-06 | pass→fail | 9,306 | 7,662 | -18% | 1 | 1 | 0% | 2,105 | 1,519 | -28% | 0 | 0 | — |
case-07 | fail→pass | 10,352 | 3,392 | -67% | 1 | 1 | 0% | 1,651 | 1,541 | -7% | 0 | 0 | — |
case-09 | pass→pass | 6,353 | 1,726 | -73% | 1 | 1 | 0% | 1,272 | 1,145 | -10% | 0 | 0 | — |
case-10 | pass→pass | 4,779 | 3,032 | -37% | 1 | 1 | 0% | 923 | 1,382 | +50% | 0 | 0 | — |
case-11 | pass→pass | 10,044 | 2,762 | -73% | 1 | 1 | 0% | 1,973 | 1,276 | -35% | 0 | 0 | — |
case-12 | fail→pass | 11,737 | 2,702 | -77% | 1 | 1 | 0% | 2,091 | 1,411 | -33% | 0 | 0 | — |
case-13 | pass→pass | 4,837 | 2,689 | -44% | 1 | 1 | 0% | 845 | 1,342 | +59% | 0 | 0 | — |
case-14 | fail→pass | 7,342 | 2,720 | -63% | 1 | 1 | 0% | 1,421 | 1,323 | -7% | 0 | 0 | — |
case-15 | pass→pass | 12,087 | 1,639 | -86% | 1 | 1 | 0% | 2,116 | 1,062 | -50% | 0 | 0 | — |
case-16 | fail→pass | 4,436 | 3,933 | -11% | 1 | 1 | 0% | 824 | 1,557 | +89% | 0 | 0 | — |
case-17 | fail→fail | 5,885 | 1,870 | -68% | 1 | 1 | 0% | 965 | 1,115 | +16% | 0 | 0 | — |
case-18 | fail→pass | 3,648 | 1,801 | -51% | 1 | 1 | 0% | 715 | 1,075 | +50% | 0 | 0 | — |
case-19 | fail→pass | 9,188 | 2,454 | -73% | 1 | 1 | 0% | 1,443 | 1,298 | -10% | 0 | 0 | — |
case-20 | pass→pass | 10,704 | 3,790 | -65% | 1 | 1 | 0% | 1,867 | 1,502 | -20% | 0 | 0 | — |
case-21 | fail→pass | 8,343 | 1,515 | -82% | 1 | 1 | 0% | 1,538 | 1,038 | -33% | 0 | 0 | — |
case-22 | fail→fail | 4,251 | 1,576 | -63% | 1 | 1 | 0% | 662 | 1,089 | +65% | 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, and 16 counted toward the lift figure. The other 6 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +23 percentage points is the difference between those two pass rates over the 16 comparable cases. 3 cases got worse with the skill loaded, and they are included in that figure.
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.