Skip to main content
affpapa.org
RU EN
skill Claude Code CX Codex Cursor GitHub Copilot

cost-conversation — Claude Code skill: what it does, how to install

Groups LLM spending by session, displaying start time, message count, top model, and total cost. Helps evaluate long or expensive conversations.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add ruvnet/ruflo --skill cost-conversation -a claude-code
Open on GitHub

What cost-conversation does

The skill breaks down tracked spend by individual conversation rather than by agent or model. This makes it straightforward to pinpoint specific sessions that ran long or consumed expensive model tiers. Output includes a markdown table with conversation start times, session ID prefixes, message counts, top models, and costs.

Execution relies on the Bash tool. The agent runs node plugins/ruflo-cost-tracker/scripts/conversation.mjs. You can control output with environment variables: CONV_LIMIT=20 restricts output to twenty recent sessions, CONV_FORMAT=json switches markdown to JSON, and CONV_NAMESPACE overrides the target namespace.

The skill will fail without Node.js available in the environment to execute the .mjs script. It also depends strictly on existing tracking data populated earlier by cost-track.

What it helps with

  • spot the most expensive conversation sessions
  • check average session cost before scoping long tasks
  • isolate project-specific expenses using CONV_NAMESPACE
  • export session-level cost rollups as JSON

Example prompts for the agent

  • Show me total spend per conversation.
  • List the last 20 sessions and their cost in JSON using cost-conversation.
  • Roll up conversation costs for namespace cost-tracking-core.

How to install cost-conversation

1Skills CLI (Vercel)

npx skills add ruvnet/ruflo --skill cost-conversation -a claude-code

2Manually: put the files in place

~/.claude/skills/cost-conversation/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/cost-conversation/

From the same set104

The whole set →
ruflo ruvnet This skill adds multi-agent orchestration, memory, routing, and MCP tools to a project. Use it for swarm tasks and multi-step workflows. Claude Code CX Codex Cursor +1 4,000installs Swarm Orchestration ruvnet Skill for managing agent swarms with parallel execution, dynamic topology, and automatic load balancing. Use when a single agent is not enough and you need to orchestrate specialists of different types. Claude Code CX Codex Cursor +1 2,100installs github-project-management ruvnet Turns issue triage and board upkeep into gh and ruv-swarm calls: labels, subtasks, duplicate lookup. Useful when the tracker holds more tickets than order. Claude Code CX Codex Cursor +1 1,400installs github-workflow-automation ruvnet Automates GitHub Actions with AI agent coordination. Generates optimised pipelines, manages pull requests, analyzes failed runs, and deploys updates with risk assessment. Claude Code CX Codex Cursor +1 1,300installs github-code-review ruvnet Runs a swarm of specialized AI agents to inspect GitHub pull requests for security, performance, and architecture issues. Claude Code CX Codex Cursor +1 1,300installs stream-chain ruvnet Chains sequential agent steps together using streaming JSON flow and provides ready-to-run pipelines. Claude Code CX Codex Cursor +1 1,200installs flow-nexus-swarm ruvnet Deploy cloud-based AI agent swarms and define event-driven workflows with message queues. Use it to coordinate tasks, inspect runs, and scale a swarm. Claude Code CX Codex Cursor +1 1,200installs performance-analysis ruvnet Detects bottlenecks in Claude Flow swarms, profiles agent operations, and generates reports with actionable optimization recommendations. Claude Code CX Codex Cursor +1 1,200installs

Similar

godot-nodes-scenes gamedev-skills Teaches the agent to build a Godot 4.7 project from nodes and scenes: reusable .tscn files, runtime instancing, autoload singletons, and node lookups that survive renames. Claude Code CX Codex Cursor +1 6,200installs ce-explain EveryInc A skill that explains how a piece of code or a stretch of work ended up in its current shape, with the evidence it used. For the reasoning, not the recommendation. Claude Code CX Codex Cursor +1 952installs figma-create-new-file figma A skill that tells the agent how to create a Figma Design, FigJam or Slides file with the MCP create_new_file tool, including which plan and editor type to use. Claude Code CX Codex Cursor +1 3,400installs setup-matt-pocock-skills Matt Pocock This skill configures a repository for Matt Pocock's engineering skills by setting its issue tracker, triage labels, and domain docs layout. Run it before using the other skills. Claude Code 1,052,851installs to-tickets Matt Pocock Turns a plan, spec, or conversation into small end-to-end tickets with explicit blockers. Use it to agree on the work breakdown before tickets go to a tracker. Claude Code 711,230installs writing-plans Jesse Vincent This skill turns requirements for a multi-step task into an implementation plan before code changes begin. It helps when another engineer needs exact files, interfaces, and checks. Claude Code CX Codex 282,859installs caveman-review JuliusBrussee Turns code review comments into one line per finding: location, problem, fix. Useful when a diff or PR needs a fast pass without the filler. Claude Code CX Codex Cursor +1 410,700installs caveman-compress JuliusBrussee Compresses CLAUDE.md, todo lists, and other prose files into a shorter format while retaining a readable backup. Claude Code CX Codex Cursor +1 410,300installs

Questions about cost-conversation

How do I install cost-conversation in Claude Code?

Run npx skills add ruvnet/ruflo --skill cost-conversation -a claude-code.

How does cost-conversation differ from cost-report?

While cost-report aggregates expenses across agents and models, cost-conversation breaks spend down per conversation session.

What tools and environment variables does it support?

It requires the Bash tool and Node.js to execute conversation.mjs. You can pass CONV_FORMAT=json, CONV_LIMIT=20, and CONV_NAMESPACE=cost-tracking.

Source text

SKILL.md · MIT 
---
name: cost-conversation
description: Per-conversation cost view — list every session in cost-tracking with started-at, message count, top model, and total cost
argument-hint: ""
allowed-tools: Bash
---

# 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

1. **Run the script** from anywhere:

   ```bash
   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

2. **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).

## Cross-references

- `cost-track` — the producer that populates `cost-tracking:session-*`
- `cost-report` — same data, per-agent / per-model lens
- `cost-trend` — drift across bench runs (different axis: corpus runs vs conversations)
- `cost-budget-check` — sums across conversations to evaluate the budget threshold

© ruvnet · MIT · ruvnet/ruflo

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor