Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/paulrobello/par_cc_usage/claude-mdgit clone --depth 1 https://github.com/paulrobello/par_cc_usageWrote 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.
[](https://agentmods.dev/instructions/paulrobello/par_cc_usage/claude-md)<a href="https://agentmods.dev/instructions/paulrobello/par_cc_usage/claude-md"><img src="https://agentmods.dev/badge/instructions/paulrobello/par_cc_usage/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00714 | $0.00714 |
| Opus 5 | $0.00357 | $0.00357 |
| Sonnet 5 | $0.00143 | $0.00143 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
par_cc_usage 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
PAR CC Usage is a Python CLI tool for tracking and analyzing Claude Code token usage. It monitors JSONL files, provides real-time statistics with cost tracking, and manages 5-hour billing blocks.
Quick Start
# Setup
uv sync
# Run monitor
make dev # Development mode with hot reload
make run # Normal mode
uv run pccu monitor
# Code quality (run before commits)
make checkall # Format, lint, and typecheck
# Testing
make test
Key Commands
Status Line Integration
# Install/uninstall Claude Code status line
uv run pccu install-statusline [--force]
uv run pccu uninstall-statusline [--force]
Status line shows: [project] · 🪙 tokens · 💰 cost · ⏱️ time · SES:model · session_tokens
Monitor Options
uv run pccu monitor # Default: tools and pricing enabled
uv run pccu monitor --no-tools # Disable tool usage display
uv run pccu monitor --no-pricing # Disable pricing display
uv run pccu monitor --no-p90 # Use absolute max instead of P90
uv run pccu monitor --snapshot # Single snapshot and exit
Configuration & Export
# Update config maximums
uv run pccu update-maximums [--dry-run] [--force]
# Export data
uv run pccu list --format json --output costs.json
uv run pccu list --format csv --output costs.csv
Troubleshooting
# Cache issues
uv run pccu clear-cache # Clear and rebuild cache
uv run pccu monitor --no-cache # Run without cache
# Debug commands
uv run pccu debug-unified # Debug block calculation
uv run pccu test-webhook # Test notifications
Development Guidelines
Version Management
- ONLY bump version when user requests it
- Version source:
src/par_cc_usage/__init__.pyline 3 - Update README.md "What's New" section when bumping
Code Standards
- Cyclomatic complexity ≤ 10
- Type annotations required
- Google style docstrings
- Run
make checkallbefore commits
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.
- 6d ago First seen · 98 lines · 714 tokens per session scan A f4232d71e4ab
par_cc_usage CLAUDE.md is an instructions file published in the GitHub repository paulrobello/par_cc_usage (84 stars, last pushed 2mo ago), licensed MIT. It adds 714 tokens to every session, about $0.0036 per session on Opus 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.
Other instructions, from other repositories
terminal-browser AGENTS.md
AGENTS.md instructions for zenbu-labs/terminal-browser, a project described as: A browser inside your terminal.
liney AGENTS.md
AGENTS.md instructions for everettjf/liney, covering liney repository collaboration guide, 交流语言 / communication language, project overview, repository layout and build and test.
superset AGENTS.md
AGENTS.md instructions for superset-sh/superset, covering superset monorepo, project structure, exception: shadcn/ui components, database and releases.
superset CLAUDE.md
Claude Code instructions for superset-sh/superset, a project described as: Superset is an agentic IDE to orchestrate 100+ coding agents in parallel. Run any agent with your own subscription.
silo AGENTS.md
AGENTS.md instructions for silo-code/silo, covering silo — project guide for coding agents, engineering principles, self-documentation — keep docs in sync as you build, planning a substantial change and domain language — keep the glossary in sync as you build.
code-by-wire CLAUDE.md
Instructions for luojiahai/code-by-wire, covering claude.md, development, website, architecture and code style.