Cost Conversation

While cost-report shows you spending by agent and model, this gives you the per-conversation view: which individual sessions burned through the most tokens. You run a Node script that reads from the cost-tracking namespace and get back a markdown table with session start time, message count, top model used, and total cost for each conversation. It's the retrospective lens you want when you need to answer "why did that Opus session cost $12" or figure out if your typical project sessions are staying under budget. Works anywhere you've got cost-track running, and you can scope it to a specific project namespace if you're tracking multiple workstreams.

skills.sh installs: 682
GitHub stars: 81.4K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add ruvnet/ruflo --skill cost-conversation --agent claude-code

Installs into .claude/skills of the current project.

Files

Cost per Conversation

cost-report and cost-optimize aggregate by agent and model. This skill aggregates by conversation (session) — a different lens that surfaces which conversations cost the most. Useful for retrospectives ("which sessions ran long on Opus?") and for evaluating whether a given project's session pattern is sustainable.

When to use

After multiple sessions, to see total spend per conversation.
Before scoping a long session, to understand typical cost-per-conversation.
For per-project rollups via CONV_NAMESPACE=cost-tracking-<project>.

Steps

Run the script from anywhere:
```
node plugins/ruflo-cost-tracker/scripts/conversation.mjs
```
Optional env:
- CONV_FORMAT=json — emit JSON instead of markdown
- CONV_LIMIT=20 — show only the most recent N conversations
- CONV_NAMESPACE=cost-tracking — override target namespace
Inspect the markdown table — total cost across all conversations, per-tier rollup, then a per-session table (started-at, sessionId prefix, message count, top model, cost).