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/lasswellt/cc-metrics/claude-mdgit clone --depth 1 https://github.com/lasswellt/cc-metricsWrote 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/lasswellt/cc-metrics/claude-md)<a href="https://agentmods.dev/instructions/lasswellt/cc-metrics/claude-md"><img src="https://agentmods.dev/badge/instructions/lasswellt/cc-metrics/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 | $0.04657 | $0.04657 |
| Opus 5 | $0.02329 | $0.02329 |
| Sonnet 5 | $0.00931 | $0.00931 |
| Haiku 4.5 | $0.00466 | $0.00466 |
Grade A, and why
cc-metrics CLAUDE.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl http://localhost:4318/api/debug/metrics # View raw metrics How it starts
The opening of the file, as written. The whole thing — 564 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
Claude Code Metrics Dashboard is a Node.js application that monitors Claude Code usage via OpenTelemetry Protocol (OTLP). It receives telemetry data from Claude Code, stores it in RethinkDB, and displays real-time metrics through a web dashboard.
Essential Commands
Development
npm start # Start the dashboard server
npm run dev # Same as start (alias)
npm run debug # Start with DEBUG=true for verbose logging
npm run recalc-stats # Recalculate aggregated stats from sessions
Database Setup
npm run setup # Initialize RethinkDB database schema
# (Runs automatically on first server start)
Note: Database setup happens automatically when you first start the server. The npm run setup command is useful for:
- Manual initialization before starting the server
- Troubleshooting database issues
- CI/CD pipelines
- Verifying database connectivity
Testing
Test the OTLP endpoint manually:
curl http://localhost:4318/api/debug/metrics # View raw metrics
curl http://localhost:4318/api/debug/stats-comparison # Compare session totals vs aggregated stats
Database
rethinkdb --http-port 8081 # Start RethinkDB server (web UI on port 8081)
docker run -d --name rethinkdb \ # Run RethinkDB in Docker
-p 28015:28015 -p 8081:8080 rethinkdb
Git Workflow
CRITICAL: The main branch is protected. Always create a feature branch for your work.
Branch Management Rules
-
Always create a new branch for each session/task
git checkout -b feature/descriptive-name # Example: feature/add-cost-tracking # Example: fix/metrics-aggregation-bug -
Branch naming conventions:
feature/- New features or enhancementsfix/- Bug fixesrefactor/- Code refactoringdocs/- Documentation updatestest/- Test additions or updates
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 · 564 lines · 4,657 tokens per session scan A 48e3b160d562
cc-metrics CLAUDE.md is an instructions file published in the GitHub repository lasswellt/cc-metrics (10 stars, last pushed 6mo ago), licensed MIT. It adds 4,657 tokens to every session, about $0.0233 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
Vibe-Research AGENTS.md
AGENTS.md instructions for simonlin1212/Vibe-Research, covering vibe-research-agent 金融研究宪法, 0. 三条不可越线, 1. 数据纪律(五问 gate:给出任何数字或结论前逐条自问), 2. 研究哲学(评估框架,不是预测工具) and 3. 估值口径(你只选输入、解释输出;计算交给 calc/).
worldmonitor AGENTS.md
AGENTS.md instructions for koala73/worldmonitor, covering agents.md, task mode and authority, start here, surface routing and architecture invariants.
vizro copilot-instructions.md
Copilot instructions for mckinsey/vizro, covering github copilot instructions for vizro, pull requests from bots and automated tooling and everything else.
openclaw-dashboard CLAUDE.md
Claude Code instructions for mudrii/openclaw-dashboard, covering go development standards, project constraints, internal packages, environment and commands.
metabase copilot-instructions.md
Copilot instructions for metabase/metabase, covering metabase developer assistant instructions, code review standards, security critical issues, performance red flags and code quality essentials.
clawmetry AGENTS.md
AGENTS.md instructions for vivekchand/clawmetry, covering agents.md — for ai coding agents, quick context, where new code goes (open-core split), the rules that bite and common tasks.