agentmods.dev

ccmonitor CLAUDE.md

A set of project instructions for ccmonitor, a Bun terminal app that watches Claude Code activity and displays sessions, tools, tasks, token use, and changed files. It also documents how to build, run, test, and upgrade the app.

In plain words
What is it for?
Guiding development, builds, manual verification, and upgrades of the ccmonitor project.
Why use it?
It gives coding agents the project context and expected commands, reducing mistakes when changing or checking the application.

Instructions file

54 1mo ago A scan 1,158 tokens original MIT
View the source file tobyilee/ccmonitor
Install

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.

agentmods
npx agentmods add instructions/tobyilee/ccmonitor/claude-md
Clone the repo
git clone --depth 1 https://github.com/tobyilee/ccmonitor
Per session 1,158 This file is loaded in full into every session.
When invoked 1,158 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01158 $0.01158
Opus 5 $0.00579 $0.00579
Sonnet 5 $0.00232 $0.00232
Haiku 4.5 $0.00116 $0.00116

Measured 2d ago against content hash 5c7da552d948, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ccmonitor 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 2d 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 · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 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

ccmonitor — A standalone Bun TUI app that monitors Claude Code session activity in real time. It watches ~/.claude/ data files (JSONL transcripts, subagent metadata, team configs, task files) and renders a terminal dashboard showing tool usage, skills, subagents, teams, tasks, token consumption, and file activity.

Build & Run Commands

bun run start          # Run the monitor (bun run src/index.ts)
bun run dev            # Run with --watch for auto-reload
bun run build          # Compile to standalone binary: dist/ccmonitor
bun run install:global # Build + copy binary to ~/.bun/bin/ccmonitor

Run with a specific session: bun run src/index.ts <sessionId>

Testing

No test suite exists yet (bun test is not wired up). Verification is manual:

  1. bun run build must succeed.
  2. bun run start must render visually-identical TUI output to the prior version.
  3. A bun test setup is planned — see tasks/prd-quality-uplift.md US-002 / US-005.

Upgrade

When the user says upgrade:

  • Bump the minor version in package.json
  • Verify with bun run build (rebuild dist/ccmonitor)
  • Add an entry to CHANGELOG.md (Keep a Changelog format)
  • Update README.md (version line + any user-facing changes)
  • Save, commit, push

Architecture

Four source files in src/, no external UI framework — raw ANSI escape codes to stdout:

  • index.ts — Entry point. Sets up chokidar file watcher on ~/.claude/ paths, manages keyboard input (q/r), runs a 2-second setTimeout refresh loop calling refreshState() → render(). Maintains a ring buffer of file events (max 50).
  • parser.ts — All data extraction logic. findLatestSession(cwd) locates the most recent .jsonl transcript for a project. parseTranscript() reads the JSONL line-by-line and builds SessionState by processing each entry for: tool usage counts, skill invocations (both slash-command <command-name> tags and Skill tool_use blocks), token/message counters, model info, team references. After transcript parsing, loads subagent metadata, team configs, tasks, and hook state from disk.
  • types.ts — All TypeScript interfaces. SessionState is the central data structure; TranscriptEntry models the JSONL schema.
  • ui.ts — Pure rendering. Builds ANSI box-drawing output from SessionState. Handles CJK fullwidth character widths for correct terminal alignment. No state mutation.

Read the full file on GitHub · 71 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. 2d ago First seen · 71 lines · 1,158 tokens per session scan A 5c7da552d948

Subscribe to this mod's changes

ccmonitor CLAUDE.md is an instructions file published in the GitHub repository tobyilee/ccmonitor (54 stars, last pushed 1mo ago), licensed MIT. It adds 1,158 tokens to every session, about $0.0058 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.

Testing
Related

Other instructions, from other repositories

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

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 · 6,785 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 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 · 4,345 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js 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 · 7,296 tokens