watch

watch is a command for Claude Code from Marcel-Bich/marcel-bich-claude-marketplace. It costs 11 tokens per session (1,079 once invoked), scanned A, original, MIT.

A command for watching background coding agents while they work. It reports whether agents are running, waiting, blocked, or finished.

In plain words
What is it for?
Use it to monitor parallel agent tasks and choose actions such as resuming, reviewing output, or stopping an agent.
Why use it?
It removes the need to inspect each agent’s output file separately to understand progress.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the TodoWrite tool.

Part of the hydra plugin — 9 commands shipped together

Good fit Use it to monitor parallel agent tasks and choose actions such as resuming, reviewing output, or stopping an agent.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/marcel-bich/marcel-bich-claude-marketplace/watch
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/Marcel-Bich/marcel-bich-claude-marketplace

Made for: Claude Code.

Or install hydra, the plugin that ships this one along with the rest of its 9 commands.

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 watch

README.md
[![agentmods](https://agentmods.dev/badge/commands/marcel-bich/marcel-bich-claude-marketplace/watch/github.svg)](https://agentmods.dev/commands/marcel-bich/marcel-bich-claude-marketplace/watch)
Your own site
<a href="https://agentmods.dev/commands/marcel-bich/marcel-bich-claude-marketplace/watch"><img src="https://agentmods.dev/badge/commands/marcel-bich/marcel-bich-claude-marketplace/watch/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for watch

Your own site · 80×15
<a href="https://agentmods.dev/commands/marcel-bich/marcel-bich-claude-marketplace/watch"><img src="https://agentmods.dev/badge/commands/marcel-bich/marcel-bich-claude-marketplace/watch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,079 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00011 $0.01079
Opus 5 $0.00005 $0.00540
Sonnet 5 $0.00002 $0.00216
Haiku 4.5 $0.00001 $0.00108

Measured 8d ago against content hash 0db70a341c3b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

watch 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 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.

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.

plugins/hydra/commands/watch.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hydra Watch

You are executing the /hydra:watch command. Live monitoring of all background agents with real-time status updates.

Purpose

Monitor multiple background agents running in parallel:

  • Poll agent output files for current status
  • Display live table with agent progress
  • Detect blocked/completed/waiting states
  • Offer actions: resume, check output, kill

Process

1. Find Running Agents

# Get project path for task directory
PROJECT_PATH=$(pwd | sed 's|/|\\-|g' | sed 's|^\\-||')
TASK_DIR="/tmp/claude/${PROJECT_PATH}/tasks"

# List all agent output files
ls -la "$TASK_DIR"/*.output 2>/dev/null || echo "No agents found"

2. Parse Agent Status

For each .output file, extract the current status:

for f in "$TASK_DIR"/*.output; do
  AGENT_ID=$(basename "$f" .output)

  # Get last meaningful lines (skip empty lines)
  LAST_ACTION=$(tail -50 "$f" | grep -v '^$' | tail -5)

  # Detect status
  if echo "$LAST_ACTION" | grep -qi "completed\|finished\|done"; then
    STATUS="completed"
  elif echo "$LAST_ACTION" | grep -qi "blocked\|denied\|permission"; then
    STATUS="blocked"
  elif echo "$LAST_ACTION" | grep -qi "waiting\|user input\|confirmation"; then
    STATUS="waiting"
  else
    STATUS="running"
  fi

  echo "$AGENT_ID|$STATUS|$LAST_ACTION"
done

3. Display Status Table

Format output as a clear table:

Hydra Watch - Live Agent Monitor
================================

  Agent   | Status    | Current Action
  --------|-----------|------------------------------------------
  a81dddd | running   | Optimizing Playwright config...
  abc3593 | running   | Running tests...
  adb39f1 | blocked   | git commit blocked by DOGMA-PERMISSIONS
  af848c1 | completed | All tasks finished
  ac49e7c | waiting   | Waiting for user confirmation

Last updated: 00:42:15 | Polling every 5s

4. Detect Problems

Check for common blockers:

# DOGMA-PERMISSIONS blocks
grep -l "DOGMA-PERMISSIONS\|git commit.*blocked\|git push.*blocked" "$TASK_DIR"/*.output 2>/dev/null

# Permission denied
grep -l "permission denied\|BLOCKED by" "$TASK_DIR"/*.output 2>/dev/null

# Waiting for input
grep -l "waiting for\|user input\|confirmation" "$TASK_DIR"/*.output 2>/dev/null

Read the full file on GitHub · 168 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 · 168 lines · 11 tokens per session scan A 0db70a341c3b

Subscribe to this mod's changes

watch is a command published in the GitHub repository Marcel-Bich/marcel-bich-claude-marketplace (13 stars, last pushed 2d ago), licensed MIT. It adds 11 tokens to every session and 1,079 once invoked, about $0.0001 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 2026-09-03.