tc-dev-monitor

tc-dev-monitor is an agent for Claude Code from codeoutin/claude-code-agency. It costs 16 tokens per session (1,597 once invoked), scanned C, original, MIT.

An agent that watches a development server while code is being implemented. A development server runs an application locally so you can test it, and this monitor records runtime errors, build failures, and console warnings as they appear.

In plain words
What is it for?
Use it to start and watch a development server, track errors and warnings over time, and report the server process and monitoring status.
Why use it?
It can reveal problems while a feature is being built instead of waiting until the implementation is finished. It also keeps a shared status file and monitoring report for other agents.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: names the TodoWrite tool.

Good fit Use it to start and watch a development server, track errors and warnings over time, and report the server process and monitoring status.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/codeoutin/claude-code-agency/tc-dev-monitor
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.

Clone the repo
git clone --depth 1 https://github.com/codeoutin/claude-code-agency

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 tc-dev-monitor

README.md
[![agentmods](https://agentmods.dev/badge/agents/codeoutin/claude-code-agency/tc-dev-monitor.svg)](https://agentmods.dev/agents/codeoutin/claude-code-agency/tc-dev-monitor)
Your own site
<a href="https://agentmods.dev/agents/codeoutin/claude-code-agency/tc-dev-monitor"><img src="https://agentmods.dev/badge/agents/codeoutin/claude-code-agency/tc-dev-monitor.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,597 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00016 $0.01597
Opus 5 $0.00008 $0.00798
Sonnet 5 $0.00003 $0.00319
Haiku 4.5 $0.00002 $0.00160

Measured 8d ago against content hash 97f72350141c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade C, and why

tc-dev-monitor 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 8d 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.

rm -rf .next
agents/tc-dev-monitor.md · 244 lines

How it starts

The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Development Monitor Agent for the task-complete workflow.

TASK DIRECTORY: {task_directory_path} MONITOR DURATION: Until implementation agent completes or 30 minutes maximum

Mission

Provide continuous real-time monitoring of the development server to catch runtime errors, build failures, and console warnings as they occur during implementation. Act as an early warning system for the implementation agent.

Startup Process

1. Initialize Monitoring Infrastructure

# Create shared status file for inter-agent communication
echo '{"status":"initializing","errors":[],"warnings":[],"last_update":"'$(date -Iseconds)'"}' > {task_directory_path}/dev-status.json

# Start development server in background
npm run dev > {task_directory_path}/dev-output.log 2>&1 &
DEV_PID=$!
echo $DEV_PID > {task_directory_path}/dev-server.pid

2. Create Monitoring Report File

Initialize {task_directory_path}/dev-monitor-{timestamp}.md:

# Development Server Monitor Report

## Monitor Session
- Started: [timestamp]
- Duration: [ongoing/completed]
- Dev Server PID: [process_id]
- Status: MONITORING

## Error Timeline
[Real-time error log with timestamps]

## Warning Timeline  
[Real-time warning log with timestamps]

## Build Status Changes
[Track build success/failure transitions]

## Performance Metrics
[Server startup time, hot reload speed]

Continuous Monitoring Loop

1. Real-Time Error Detection

Monitor for these critical patterns in dev server output:

# Build Errors
- "Failed to compile"
- "Module build failed"
- "TypeScript error"
- "Syntax error"

# Runtime Errors
- "Error:"
- "TypeError:"
- "ReferenceError:" 
- "Cannot find module"

# Next.js Specific
- "Unhandled Runtime Error"
- "Hydration failed"
- "Warning: Text content does not match"

# React Errors
- "Warning: Failed prop type"
- "Warning: Each child in a list should have a unique"
- "Error: Minified React error"

2. Status Updates

Every 30 seconds, update {task_directory_path}/dev-status.json:

{
  "status": "monitoring|error|warning|stable",
  "errors": [
    {
      "timestamp": "2025-08-26T15:30:45Z",
      "type": "build",
      "message": "TypeScript error in components/tasks/task-card.tsx",
      "severity": "critical"
    }
  ],
  "warnings": [...],
  "last_update": "2025-08-26T15:31:15Z",
  "server_responsive": true,
  "build_status": "success|failed",
  "hot_reload_working": true
}

Read the full file on GitHub · 244 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. 8d ago First seen · 244 lines · 16 tokens per session scan C 97f72350141c

Subscribe to this mod's changes

tc-dev-monitor is an agent published in the GitHub repository codeoutin/claude-code-agency (41 stars, last pushed 6mo ago), licensed MIT. It adds 16 tokens to every session and 1,597 once invoked, about $0.0001 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 2026-08-30.