What is context-stats CLAUDE.md?

Project instructions for context-stats, a tool that monitors how much of Claude Code's conversation context remains and shows it with live text graphs.

It helps developers modify the Python statusline, maintain its CSV state files, understand the project structure, and run its tests and coverage checks.

It documents the project's purpose, implementation, CSV data format, and test commands so changes follow the expected contract.

How luongnv89/context-stats configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to luongnv89/context-stats. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/luongnv89/context-stats/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/luongnv89/context-stats

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/luongnv89/context-stats/claude-md/github.svg)](https://agentmods.dev/instructions/luongnv89/context-stats/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/luongnv89/context-stats/claude-md"><img src="https://agentmods.dev/badge/instructions/luongnv89/context-stats/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/luongnv89/context-stats/claude-md"><img src="https://agentmods.dev/badge/instructions/luongnv89/context-stats/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 3,901 This file is loaded in full into every session.

When invoked 3,901 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.03901	$0.03901
Opus 5.5	$0.01560	$0.01560
Sonnet 5.5	$0.00780	$0.00780
Haiku 4.5	$0.00390	$0.00390

Measured 25d ago against content hash 063585e7a37e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

context-stats CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 25d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Project Purpose

context-stats provides real-time context window monitoring for Claude Code sessions. It tracks token consumption over time and displays live ASCII graphs so users can see how much context remains.

Implementation

The statusline is implemented in Python. Claude Code invokes the statusline script via stdin JSON pipe — the script reads JSON from stdin and writes formatted text to stdout. The Python implementation persists state to CSV files read by the context-stats CLI. The standalone statusline lives at scripts/statusline.py (Python 3, state-writing, pip-installable via the package).

CSV Format Contract

State files are append-only CSV at ~/.claude/statusline/statusline.<session_id>.state with 15 comma-separated fields. See docs/CSV_FORMAT.md for the full field specification. Key constraint: workspace_project_dir has commas replaced with underscores before writing.

Test Commands

# Python tests (canonical — matches docs/DEVELOPMENT.md agent setup notes)
source venv/bin/activate && pytest tests/python/ -q -p no:cacheprovider

# Coverage (enforces the --cov-fail-under=94 floor from pyproject.toml addopts)
pytest tests/python/ -q -p no:cacheprovider --cov=src/claude_statusline --cov-report=term

Verification Gates

After editing anything under src/ or scripts/statusline.py, run from the activated venv:

ruff check .
mypy src scripts

IMPORTANT: work is not done until lint, typecheck, and tests all pass.

Key Architectural Decisions

Append-only CSV state files with rotation at 10,000 lines (keeps most recent 5,000); append+rotation serialized under a best-effort fcntl exclusive lock
No network requests — all data stays local in ~/.claude/statusline/
Session ID validation — rejects /, \, .., null bytes, plus comma/newline/control characters (CSV safety) for path-traversal and column-shift defense
5-second git command timeout in the Python implementation
Config via ~/.claude/statusline.conf — simple key=value pairs

Read the full file on GitHub · 115 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

25d ago Changed · +1 lines · +177 tokens per session 063585e7a37e
2mo ago Changed · +24 tokens per session c1042867d0c4
2mo ago First seen · 114 lines · 3,700 tokens per session scan A 678934846795

Subscribe to this mod's changes

context-stats CLAUDE.md is an instructions file published in the GitHub repository luongnv89/context-stats (118 stars, last pushed 22d ago), licensed MIT. It adds 3,901 tokens to every session, about $0.0156 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Memory and context context stats

context-stats CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
context-stats CLAUDE.mdluongnv89/context-stats	Instructions file	118	22d ago	MIT	A	3,901	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

context-stats: Instructions file for Claude Code