claudewatch CLAUDE.md

claudewatch CLAUDE.md is an instructions file for Claude Code from blackwell-systems/claudewatch. It costs 3,838 tokens per session, scanned C, original, MIT.

Project-specific instructions for Claudewatch, a tool that monitors Claude Code sessions and reports on agent behavior over time. It explains the project’s architecture, commands, data files, and development practices.

In plain words
What is it for?
Use it when changing Claudewatch’s Go code, command-line tools, hooks, MCP tools, SQLite data layer, or web interface.
Why use it?
It gives a coding agent the background needed to work safely within Claudewatch’s monitoring, analytics, and local-data design.

Instructions file for Claude Code

Written for Claude Code: PostToolUse hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/dayna.blackwell/code/claudewatch/PLAN.md.

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

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 claudewatch CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/blackwell-systems/claudewatch/claude-md.svg)](https://agentmods.dev/instructions/blackwell-systems/claudewatch/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/blackwell-systems/claudewatch/claude-md"><img src="https://agentmods.dev/badge/instructions/blackwell-systems/claudewatch/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,838 This file is loaded in full into every session.
When invoked 3,838 The same file — it is already loaded in full.
Security scan C 1 finding. 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 5.1 $0.03838 $0.03838
Opus 5 $0.01919 $0.01919
Sonnet 5 $0.00768 $0.00768
Haiku 4.5 $0.00384 $0.00384

Measured 6d ago against content hash cccfe52c9d5f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade C, and why

claudewatch CLAUDE.md scanned grade C 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

**Solution:** `rm -rf ~/.claude/usage-data/session-meta/*.json && claudewatch scan`
CLAUDE.md · 296 lines

How it starts

The opening of the file, as written. The whole thing — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Instructions for claudewatch

AgentOps for Claude Code. Real-time monitoring and behavioral intervention for AI agents + post-session analytics for developers.

Project Overview

claudewatch is AgentOps infrastructure for AI agent development. It monitors Claude Code sessions during execution (via hooks and MCP tools) and provides post-session analytics (via CLI). Think DevOps for software delivery, MLOps for ML models—AgentOps is operations for AI agents.

What makes this AgentOps: Monitors agent behavior (error loops, drift, context pressure), intervenes automatically (PostToolUse hooks), provides agent self-awareness (29 MCP tools Claude queries mid-session), and offers developer analytics (friction trends, cost-per-commit, agent success rates).

Data layer: Reads local Claude data files at ~/.claude/ (no network calls except opt-in Claude API for fix --ai), computes metrics, stores snapshots in a pure-Go SQLite database.

Commands: scan (inventory + score projects), metrics (trends), gaps (friction), suggest (ranked improvements), track (snapshot diffing), log (custom metrics), fix (generate + apply CLAUDE.md patches), watch (background daemon, friction alerts).

Architecture

Three-layer AgentOps model:

  1. Push (Hooks) - SessionStart briefing + PostToolUse alerts (error loops, drift, context pressure) fire automatically
  2. Pull (MCP Tools) - 29 tools Claude queries mid-session for self-reflection (get_project_health, get_drift_signal, get_blockers)
  3. Persistent (Task Memory) - Cross-session task history and blocker tracking via extract_current_session_memory

Technical stack:

  • CLI framework: Cobra with global flags (--config, --no-color, --json, --verbose)
  • Database: modernc.org/sqlite (pure Go, no CGO, enables CGO_ENABLED=0 cross-compilation)
  • Output: lipgloss for styled tables and progress bars
  • Data flow: parsers (claude/) → analyzers (analyzer/) → suggest engine → store → output
  • Claude API integration: fixer/ calls the Anthropic API (opt-in via --ai flag, standard net/http, no external SDK). Requires ANTHROPIC_API_KEY. All other commands remain offline-only.

Read the full file on GitHub · 296 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. 6d ago First seen · 296 lines · 3,838 tokens per session scan C cccfe52c9d5f

Subscribe to this mod's changes

claudewatch CLAUDE.md is an instructions file published in the GitHub repository blackwell-systems/claudewatch (9 stars, last pushed 6mo ago), licensed MIT. It adds 3,838 tokens to every session, about $0.0192 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

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 · 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

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

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

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 · 7,296 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 · 4,469 tokens