Save user-provided or approved decisions, constraints, and facts for an AI team, then retrieve them with their sources. Keep memories separate by team and tenant, and report whether retrieval used a degraded search mode.
Generate a spending report from recorded AI usage, with token counts and USD costs grouped by model, agent, and processing tier. Check budget utilization, remaining funds, and alerts for a selected period.
Export recorded AI usage costs and budgets as Prometheus metrics or JSON. Feed external dashboards with totals, model tier breakdowns, session costs, and budget utilization, or send the same data to a webhook endpoint.
Analyze Claude Code and Codex usage logs to identify spending drivers, including cache usage, model choices, reasoning, and long sessions. Receive evidence-backed recommendations and hypothetical savings estimates to help decide which changes to try.
Connect ruflo agents running on different machines to share status, tasks, and results through signed messages. Coordinate work ownership across nodes, verify messages against registered public keys, and synchronize shared rooms over HTTP.
Check actual OpenRouter charges, API key limits, daily, weekly, and monthly spending, and account credits. Look up a single request by generation ID and report the billed model and provider returned by OpenRouter.
Compare two recorded browser sessions at matching step IDs using screenshots and accessibility snapshots, which describe page elements. Report the first difference and overall similarity to check interface changes or verify replayed sessions.
Replay recorded browser actions on the original or an alternative URL to check UI changes or reproduce bugs. When a page element cannot be found, the skill searches for a similar target and records how many steps succeeded.
Apply simple code changes across files without calling an LLM, using agent-booster's local transformation engine. The skill checks a confidence score before saving results and records outcomes for cost tracking and future routing decisions.
Run four cost checks in parallel to assess budget limits, accelerating daily spending, unusual sessions, and projected budget exhaustion. Combine their results into one health status and exit code for automated CI workflows.
Keep older web extraction commands working during migration by forwarding a supplied URL to browser-extract after displaying a deprecation notice. This compatibility shim helps existing callers transition to the replacement skill and its template option.
Plan an AI team around a goal, defining roles, deliverables, and a recorded unit budget. After approval, it creates team, run, and task records in RuFlo AI Team; it does not execute the work.
Analyze the last seven days of agent and model token usage to identify unnecessary spending. Recommend changes to model selection, prompt caching, and overlapping work, with estimated dollar savings, percentage reductions, and implementation priorities.
Review AI agent spending by conversation, with each session’s start time, message count, main model, and total cost. Use the results to identify expensive sessions and understand typical costs before planning longer work.
Compare two saved cost-summary JSON snapshots to identify changes in total spending, sessions, and model costs. Set limits on spending increases or token growth to flag cost regressions during pull request checks.
Track production session spending over time by grouping costs into configurable time windows. Compare the latest window with earlier spending averages, display the increase, and optionally return a failure exit code when it exceeds a chosen percentage.
Review an AI team's work against its acceptance criteria using collected evidence. Match requirements to task results or artifacts, distinguish verified facts from agent claims, and identify uncertainty or missing work before recommending completion.
Choose the next task using patterns learned from completed work and current progress. The skill acts on confident predictions, falls back to task priorities when confidence is low, and updates its learning after completion.
Estimate the cost per million tokens, units of model text, on hardware you own using power consumption, electricity rates, hardware costs, and measured generation speed. Compare utilization levels to find when local operation costs less than a hosted model.
Check a Ruflo installation for common environment and configuration problems, then run automatic repairs. The checks cover software versions, background services, the memory database, API keys, MCP servers, disk space, and TypeScript.
Organize an AI team's work into small tasks with one owner and one deliverable each. Record dependencies, check for duplicate tasks, and update progress so the team's recorded task state stays clear.
Run one cycle of autonomous task work in Claude Code: check progress, select and execute the next action, log the work, and schedule another cycle. Stop when all tasks are complete or the iteration limit is reached.
Find ruflo plugins suited to your current task, workflow, and installed MCP tools, which connect agents to external capabilities. Browse recommendations, search by need, and review what each candidate adds before choosing plugins.
Retrieve compacted ReasoningBank context for cost-analysis queries and summarize retrieved memories, reported token savings, cache hit rate, and package availability. The savings figure is an estimate from the integration, not a measured comparison against a baseline.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)