Cost Report
- 633 installs
- 67k repo stars
- Updated August 4, 2026
- ruvnet/ruflo
cost-report is a ruflo Claude Code skill that generates token usage and USD cost breakdowns by agent and model for developers who need real-time LLM session spend visibility.
About
cost-report is a skill in ruvnet/ruflo that builds a comprehensive cost report from claude-flow memory and agentdb retrieval tools, showing token usage, USD charges, and budget utilization for a chosen period such as today. It answers which agents and models consume the most budget and whether spend is on track. Developers reach for cost-report during Claude Code or Cursor agent sessions when finance or engineering leads need accountable LLM billing data instead of guessing from console logs. The skill accepts period arguments like `--period today` and integrates with Bash for report assembly.
- Tracks token usage and converts to dollar amounts across major LLM providers
- Generates per-session and cumulative cost reports
- Works with Claude Code, Cursor, and compatible agent runtimes
- Helps indie builders stay under budget on long-running agent tasks
- Outputs both summary tables and detailed CSV breakdowns
Cost Report by the numbers
- 633 all-time installs (skills.sh)
- +10 installs in the week ending Jul 26, 2026 (Skillselion tracking)
- Ranked #1,525 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/ruvnet/ruflo --skill cost-reportAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 633 |
|---|---|
| repo stars | ★ 67k |
| Last updated | August 4, 2026 |
| Repository | ruvnet/ruflo ↗ |
How do you track LLM agent session costs?
Get accurate, real-time cost breakdowns for Claude, Cursor, and other LLM agent sessions.
Who is it for?
Engineering leads running multi-agent Claude or Cursor workflows who need periodic token and dollar spend reports tied to agents and models.
Skip if: Teams without claude-flow memory or agentdb data stores who only need generic cloud billing dashboards unrelated to agent sessions.
When should I use this skill?
A developer asks how much agents spent, which model drove costs, or whether the current period is within budget.
What you get
Cost report with token counts, USD totals, per-agent breakdowns, and budget utilization metrics.
- token and USD cost report
- per-agent budget utilization summary
By the numbers
- Integrates with 5+ claude-flow MCP tools for memory and agentdb retrieval
Files
Cost Report
Generate a comprehensive cost report showing token usage, USD costs, and budget utilization for the specified period.
When to use
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.
Steps
1. Retrieve usage -- call mcp__claude-flow__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. 2. Compute costs -- for each record, calculate cost using model pricing:
- Haiku: $0.25/M input, $1.25/M output
- Sonnet: $3.00/M input, $15.00/M output
- Opus: $15.00/M input, $75.00/M output
- Include cache write/read costs where applicable
3. Aggregate by model -- sum costs per model, compute percentage share 4. Aggregate by tier -- classify each record as Tier 1 / Tier 2 / Tier 3 using three signals (in priority order): (a) bench data from step 1a — for any record that maps to a measured booster intent, use $0 / measured-latency directly; (b) the [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. 5. Aggregate by agent -- sum costs per agent, include the model each agent used 6. Check budget -- recall budget configuration via memory_retrieve and compute utilization percentage, check alert thresholds (50%/75%/90%/100%) 7. Report -- display: total cost, budget remaining, tier breakdown (Tier 1 / Tier 2 / Tier 3), model breakdown, agent breakdown, active alerts. See REFERENCE.md §"Cost report shape" for the canonical layout.
CLI alternative
npx @claude-flow/cli@latest memory search --query "cost report for today" --namespace cost-tracking
npx @claude-flow/cli@latest memory list --namespace cost-trackingRelated skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10How it compares
Use cost-report for agent-session token accounting inside ruflo instead of generic cloud invoices that lack per-model agent attribution.
FAQ
What data does cost-report include?
cost-report outputs token usage, USD costs, and budget utilization broken down by agent and model for the requested period. It retrieves records through claude-flow memory and agentdb search tools before assembling the summary.
When should you run cost-report?
cost-report fits when you need current spending visibility—how much each agent costs, which models dominate usage, and whether you remain within budget. Pass a period such as `--period today` to scope the report.