English Français العربية

contextburn

Official registry Developer tools

Run efficiency for coding agents: share of paid tokens that became output, not context re-reading.

Source code Website Documentation

Install

Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).

PYPI package contextburn
Claude Code 
claude mcp add contextburn -- uvx contextburn==0.2.1 mcp
JSON configuration (Claude Desktop, Cursor, VS Code) 
{
    "mcpServers": {
        "contextburn": {
            "command": "uvx",
            "args": [
                "contextburn==0.2.1",
                "mcp"
            ]
        }
    }
}

Documentation

From the project's README on GitHub, refreshed weekly. Links open on GitHub.

Contents
  1. Try it
  2. Demo
  3. Why two numbers
  4. How it counts
  5. Commands
  6. MCP server
  7. Editor extensions
  8. Menu-bar app (macOS)
  9. Limits
  10. Citing
  11. Author
  12. License

contextburn reads the transcripts Claude Code already writes on your machine and tells you what share of the tokens you paid for became model output — and how much was the agent re-reading context it had already sent.

Token counters answer "how much did I spend?". This answers "how much of it was work?" — a normalised share, so it can be compared across sessions, models and ways of working.

Try it

cp bin/contextburn ~/bin/contextburn && chmod +x ~/bin/contextburn   # python3 only, no dependencies
contextburn detail 24

Demo

Real output over the session logs of the 36 runs behind the U-curve report — nothing else on the machine. Video with DOI: 10.5281/zenodo.22713920. The runs themselves are open: Hugging Face (DOI 10.57967/hf/10366) · Kaggle · OSF (DOI 10.17605/OSF.IO/5QTWY).

Why two numbers

  • By tokens the share barely moves. Every agent step resends the accumulated context, so re-reading dominates whatever you do — it describes the agent.
  • Cost-weighted the share does move, because cached reads are priced far below fresh input and output. It depends on how you run sessions — it describes you.

The comparison above comes from a controlled experiment with its dataset and analysis scripts: Clear Every Third Task: A Measured U-Curve in the Context Economy of Coding Agents.

How it counts

  • Reads local Claude Code transcripts (~/.claude/projects/**/*.jsonl). Nothing leaves the machine — no network calls at all.
  • Deduplicates usage records by message id and keeps the element-wise maximum. A streaming runtime writes an early snapshot and a final record for the same call: counting both double-counts it, keeping only the first halves the output.
  • Weights the cost share with per-model prices kept at the top of bin/contextburn. Update them there when they change.

Commands

commandwhat it shows
contextburnwhat is burning tokens right now
contextburn detail [hours]run efficiency, sessions, and what specifically inflated the context
contextburn windowthe current 5-hour subscription window
contextburn --jsonmachine-readable state (used by the menu-bar app)
contextburn --probe <hours>raw JSON dump of the parsed sessions
contextburn --efficiency [hours]run efficiency as JSON
contextburn mcpstart the MCP server
Configuration
settingdefaultmeaning
CONTEXTBURN_LANG or ~/.config/contextburn/langeninterface language: en or ru
CONTEXTBURN_DAY_START6hour your day starts — the daily total resets here
CONTEXTBURN_WARN30000000tokens/hour that turns the menu-bar counter yellow
CONTEXTBURN_ALARM90000000tokens/hour that turns it red

The language file exists because the menu-bar app is launched from Finder, where environment variables never reach it: echo ru > ~/.config/contextburn/lang switches both the app and the CLI.

MCP server

Let the agent read its own run efficiency mid-session. The package ships a dependency-free MCP server (stdio) with two tools: run_efficiency returns the shares as structured data, and spend_breakdown returns the full report.

claude mcp add contextburn -- uvx contextburn mcp

Or install it as a Claude Code plugin, which registers the same server:

/plugin marketplace add arsentev-ai/contextburn
/plugin install contextburn@contextburn

Editor extensions

Menu-bar app (macOS)

app/main.swift is a small status-bar app. It polls contextburn --json once a minute and shows the current burn rate with an hourly graph; click a bar to see that hour's breakdown.

swiftc -O -o ContextBurn app/main.swift

Set CONTEXTBURN_BIN=/path/to/contextburn if the CLI is not in ~/bin or the usual Homebrew paths.

Limits

  • Claude Code transcripts only, for now.
  • The cost-weighted share is only as current as the price table in bin/contextburn.

Citing

Software DOI (all versions): 10.5281/zenodo.22712985. GitHub's "Cite this repository" button gives the reference; metadata is in CITATION.cff.

Author

Evgenii Arsentev — arsentev.ai · ORCID 0000-0002-9120-7298

This project was published as tokmon on its first day and renamed to avoid confusion with unrelated tools of that name; TOKMON_* environment variables still work.

License

MIT — see LICENSE.

Frequently asked questions

What is contextburn?

Run efficiency for coding agents: share of paid tokens that became output, not context re-reading.

How do I install contextburn?

It runs on your machine. In Claude Code: claude mcp add contextburn -- uvx contextburn==0.2.1 mcp. For other clients, paste the JSON configuration from this page into their MCP settings.

Does contextburn need an API key?

Its registry entry lists no required key or secret. Some features may still need an account with the service it connects to.

Is contextburn open source?

Yes. Its code is on GitHub under the MIT license.

Who maintains contextburn?

It is published by arsentev-ai. AI.tn lists it but does not maintain or endorse it.

From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.