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/vicarious11/agenttop/claude-mdgit clone --depth 1 https://github.com/vicarious11/agenttopWrote 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/vicarious11/agenttop/claude-md)<a href="https://agentmods.dev/instructions/vicarious11/agenttop/claude-md"><img src="https://agentmods.dev/badge/instructions/vicarious11/agenttop/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 | $0.01444 | $0.01444 |
| Opus 5 | $0.00722 | $0.00722 |
| Sonnet 5 | $0.00289 | $0.00289 |
| Haiku 4.5 | $0.00144 | $0.00144 |
Grade A, and why
agenttop 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 4d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agenttop — AI Usage Dashboard & Optimizer
Project Overview
agenttop is an htop-style monitoring dashboard for AI coding agents. It collects real usage data from Claude Code, Cursor, Kiro, Copilot, and Codex, then displays it in a neon-cyberpunk web dashboard with an AI-powered optimizer that generates personalized recommendations.
Architecture
Layers
Collectors → Models → Database → Web Server → Dashboard (SPA)
↓
Optimizer (Python metrics + LLM)
Key Directories
src/agenttop/collectors/— Per-tool data collectors (claude.py, cursor.py, etc.)src/agenttop/models.py— Core data models: Event, Session, ToolStatssrc/agenttop/db.py— SQLite event storesrc/agenttop/analysis/— LLM engine, intent classification, recommendationssrc/agenttop/web/— FastAPI server, optimizer, graph buildersrc/agenttop/web/static/— SPA frontend (index.html, JS, CSS)src/agenttop/tui/— Terminal UI (textual-based, alternative to web)
Data Flow
- Collectors read tool-specific data dirs (
~/.claude/,~/.cursor/, etc.) - Models normalize into Events and Sessions
- Web server aggregates via
/api/stats,/api/sessions,/api/models,/api/hours - Optimizer (
/api/optimizePOST) builds a user profile, computes deterministic metrics, sends structured JSON to LLM for intelligent analysis - Frontend renders: force-directed graph, model usage, hourly activity, sessions, cost breakdown, optimizer drawer
Build & Run
# Install (editable)
pip install -e ".[dev]"
# Web dashboard
PYTHONPATH=src python -m uvicorn agenttop.web.server:app --port 8420
# TUI
agenttop
# Tests
pytest
Code Style
- Python 3.10+, type hints everywhere
- Ruff for linting (line-length 100, select E/F/I/N/W)
# ruff: noqa: E501at top of files with long strings (optimizer.py)- Collections: prefer
defaultdict,Counterfromcollections - Async: FastAPI endpoints, sync collectors
- Frontend: vanilla JS, no frameworks, CSS custom properties for theming
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.
- 4d ago First seen · 107 lines · 1,444 tokens per session scan A 40dc8510c273
agenttop CLAUDE.md is an instructions file published in the GitHub repository vicarious11/agenttop (49 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 1,444 tokens to every session, about $0.0072 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
mcp-unity AGENTS.md
Instructions for CoderGamester/mcp-unity, covering mcp unity — ai agent guide (mcp package), purpose (what this repo is), how it works (high-level data flow), key defaults & invariants and repo layout (where to change what).
rails-ai-context AGENTS.md
AGENTS.md instructions for crisnahine/rails-ai-context, covering rails-ai-context, agent skills, issue tracker, triage labels and domain docs.
inspecto CLAUDE.md
Instructions for inspecto-dev/inspecto, covering inspecto — claude code development guide, project overview, monorepo structure, development phases (load each file as needed) and key architectural decisions.
skill.color-expert CLAUDE.md
Claude Code instructions for meodai/skill.color-expert, covering claude.md, project overview, architecture, no build/test/lint and editing guidelines.
llm-ide-rules typescript.instructions.md
Instructions for iloveitaly/llm-ide-rules, covering typescript and dates & times.
llm-ide-rules python-route-tests.instructions.md
Instructions for iloveitaly/llm-ide-rules, a project described as: Centralized LLM prompt instructions for Copilot and Cursor, including scripts to convert and sync rules for Python, React, Shell, and TypeScript. Designed for rapid reuse and contribution across projects.