Skip to content
Agentmart
Submit a tool

kco-roi

Calculate monthly token savings and ROI from using the context optimizer

Skill by egorfedorov

IndexedMIT★ 6
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/egorfedorov-kco-roi

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Calculate monthly token savings and ROI from using the context optimizer

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/kco-roi

What's inside

Skill name
kco-roi
Description
Calculate monthly token savings and ROI from using the context optimizer
License
MIT
Instructions
20 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# ROI Calculator

Calculate and display the return on investment from using Kimi Context Optimizer.

Parse $ARGUMENTS for sessions per day (default: 5).

Run:
```bash
node ${KIMI_SKILL_DIR}/../../src/roi.js $ARGUMENTS
```

Present the ROI report to the user. Highlight:
1. Monthly and yearly **token** savings — KCO is subscription-honest: tokens and % of window are the primary metric
2. Dollar savings — shown only when the user has configured `pricePerMillionInput`/`pricePerMillionOutput` in `~/.kimi-context-optimizer/config.json`
3. Team-level savings if they work in a team
4. If data comes from real sessions, note how many sessions were analyzed

If the user has no session data yet, explain that the estimate uses industry averages (35% waste) and will become more accurate as they use KCO.

From egorfedorov/kimi-context-optimizer, MIT.

More from egorfedorov/kimi-context-optimizer

Signals

Stars
6
Forks
1
Open issues
0
Last commit (this folder)
Jul 18, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from egorfedorov

Cite this page

kco-roi skill. Agent Mart. https://agentmart.dev/skills/egorfedorov-kco-roi (last updated 2026-10-24)