agentmods.dev

claude-code-usage-per-project: Instructions file for Claude Code

CLAUDE.md

claude-code-usage-per-project CLAUDE.md is an instructions file for Claude Code from jwchoi-kr/claude-code-usage-per-project. It costs 2,083 tokens per session, scanned A, original, MIT.

Project instructions for ccupp, a Claude Code status-line and usage tracker. Claude Code is a coding assistant; a status line is the small live display shown during a session.

In plain words
What is it for?
Use them when working on usage reports, daily or model breakdowns, all-project comparisons, status-line output, or prompt exports.
Why use it?
They explain the tracker’s operating modes and file structure, making it easier to change the right part without confusing session, day, model, or project reports.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is jwchoi-kr/claude-code-usage-per-project's own configuration. It tells Claude Code how to work on claude-code-usage-per-project itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-code-usage-per-project configures →

not rated 5repo 5mo ago A scan 2,083 tokens original MIT
View source ↗ jwchoi-kr/claude-code-usage-per-project
Reuse

Borrowing it

Nothing to install: this file belongs to jwchoi-kr/claude-code-usage-per-project. 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/jwchoi-kr/claude-code-usage-per-project/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/jwchoi-kr/claude-code-usage-per-project

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.

agentmods badge for claude-code-usage-per-project CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jwchoi-kr/claude-code-usage-per-project/claude-md/github.svg)](https://agentmods.dev/instructions/jwchoi-kr/claude-code-usage-per-project/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jwchoi-kr/claude-code-usage-per-project/claude-md"><img src="https://agentmods.dev/badge/instructions/jwchoi-kr/claude-code-usage-per-project/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.

agentmods 80×15 button for claude-code-usage-per-project CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jwchoi-kr/claude-code-usage-per-project/claude-md"><img src="https://agentmods.dev/badge/instructions/jwchoi-kr/claude-code-usage-per-project/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,083 This file is loaded in full into every session.
When invoked 2,083 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02083 $0.02083
Opus 5.5 $0.00833 $0.00833
Sonnet 5.5 $0.00417 $0.00417
Haiku 4.5 $0.00208 $0.00208

Measured 2mo ago against content hash f906e004c4cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claude-code-usage-per-project 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 2mo 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 · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — claude-code-usage-per-project (ccupp)

What this project is

A Claude Code status line + usage tracker. ccupp/cli.py is a thin entry point: main() dispatches by argv/TTY to one of six modes, each living in its own module:

  1. Status line — bare ccupp piped from Claude Code's statusLine hook (stdin is not a TTY); main() reads JSON from stdin and delegates rendering to ccupp/status_line.py, which prints a 2-line HUD
  2. Usage report — bare ccupp run in a terminal (TTY); ccupp/report.py prints a per-session table for the current project
  3. Daily breakdown — ccupp --daily; ccupp/daily.py prints the current project's usage grouped by local calendar day
  4. Model breakdown — ccupp --model; ccupp/model.py prints the current project's usage grouped by model
  5. All-projects comparison — ccupp --all; ccupp/all.py prints a per-project comparison table across every tracked project
  6. Export — ccupp --export; ccupp/export.py writes PROMPTS.md

Modes 2–4 are the same current-project scope sliced on a different axis: by session, by day, by model. The --daily and --model modes recompute from the raw transcripts (the per-session snapshots don't carry per-day or per-model splits), reusing the shared aggregate_by_day / aggregate_by_model helpers in ccupp/core.py.

Each user-facing mode is its own module. ccupp/core.py holds only what is shared across modes (data analysis, persistence, shared formatters). ccupp/status_line.py holds status-line presentation. Keep mode-specific logic out of ccupp/core.py.

File structure

ccupp/
  __init__.py          Package marker
  __main__.py          `python -m ccupp` entry point
  cli.py               main() dispatcher + install command
  status_line.py       Status line rendering (2-line HUD)
  core.py              Shared utilities, data analysis, persistence, table renderer
  report.py            Terminal usage report — current project (TTY mode)
  daily.py             Per-day usage breakdown — current project (--daily)
  model.py             Per-model usage breakdown — current project (--model)
  all.py               All-projects comparison report (--all)
  export.py            Prompt extraction and Markdown export (--export)
tests/
  __init__.py          Package marker
  test_cli.py          Tests for cli.py (dispatch + install)
  test_status_line.py  Tests for status_line.py
  test_core.py         Tests for core.py
  test_report.py       Tests for report.py
  test_daily.py        Tests for daily.py
  test_model.py        Tests for model.py
  test_all.py          Tests for all.py
  test_export.py       Tests for export.py
docs/                  Historical planning/spec docs — treat as context only

Read the full file on GitHub · 96 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.

  1. 2mo ago First seen · 96 lines · 2,083 tokens per session scan A f906e004c4cb

Subscribe to this mod's changes

claude-code-usage-per-project CLAUDE.md is an instructions file published in the GitHub repository jwchoi-kr/claude-code-usage-per-project (5 stars, last pushed 5mo ago), licensed MIT. It adds 2,083 tokens to every session, about $0.0083 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 2026-08-31.

Claude Codeanthropicclaudeclicost-trackingstatusbar
Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,461 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,750 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens