logs

logs is a command for Claude Code from aniketkarne/ClaudeNightsWatch. It costs 11 tokens per session (745 once invoked), scanned A, original, MIT.

A command for viewing Claude Nights Watch logs, which are records of what its background monitoring process did. The logs include prompts, responses, timestamps, status messages, and exit codes.

In plain words
What is it for?
Use it to inspect the last 50 log lines, follow the log in real time, review prompts and responses, or investigate whether a task succeeded or failed.
Why use it?
It gives you a record of task runs and errors, either from recent entries or as new entries appear.

Command for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the ClaudeNightsWatch plugin — 6 commands, 3 hooks, 1 MCP server shipped together

Good fit Use it to inspect the last 50 log lines, follow the log in real time, review prompts and responses, or investigate whether a task succeeded or failed.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add aniketkarne/ClaudeNightsWatch
Claude Code
/plugin install ClaudeNightsWatch

Made for: Claude Code.

Or install ClaudeNightsWatch, the plugin that ships this one along with the rest of its 6 commands, 3 hooks, 1 MCP server.

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 logs

README.md
[![agentmods](https://agentmods.dev/badge/commands/aniketkarne/claudenightswatch/logs.svg)](https://agentmods.dev/commands/aniketkarne/claudenightswatch/logs)
Your own site
<a href="https://agentmods.dev/commands/aniketkarne/claudenightswatch/logs"><img src="https://agentmods.dev/badge/commands/aniketkarne/claudenightswatch/logs.svg" alt="Measured on agentmods" 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 745 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 $0.00745
Opus 5 $0.00005 $0.00373
Sonnet 5 $0.00002 $0.00149
Haiku 4.5 $0.00001 $0.00075

Measured 9d ago against content hash 58bf4e8439af, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

logs 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 9d 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.

commands/logs.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

View Nights Watch Logs

Display execution logs from the Claude Nights Watch daemon, including all prompts sent to Claude, responses received, and status messages.

Usage

/nights-watch logs [OPTIONS]

Options

  • -f, --follow - Follow log file in real-time (like tail -f)
  • No options - Show last 50 lines of logs

What's Logged

Daemon Activity

  • Start/stop events
  • Configuration loaded
  • Monitoring status updates
  • Error messages and warnings

Task Execution

  • Full Prompts: Complete prompt sent to Claude (rules + task)
  • Full Responses: Everything Claude outputs during execution
  • Timestamps: Precise timing of all events
  • Exit Codes: Success/failure status

Example Log Entry

[2025-10-11 14:30:00] === Claude Nights Watch Daemon Started ===
[2025-10-11 14:30:00] PID: 12345
[2025-10-11 14:30:00] Task directory: /path/to/project
[2025-10-11 14:30:05] Task file found at /path/to/project/task.md
[2025-10-11 14:30:05] Rules file found at /path/to/project/rules.md
[2025-10-11 15:25:00] Time remaining: 2 minutes
[2025-10-11 15:27:00] Reset imminent (2 minutes), preparing to execute task...
[2025-10-11 15:28:00] Starting task execution from task.md...

=== PROMPT SENT TO CLAUDE ===
IMPORTANT RULES TO FOLLOW:
[... rules content ...]
---END OF RULES---

TASK TO EXECUTE:
[... task content ...]
---END OF TASK---
=== END OF PROMPT ===

=== CLAUDE RESPONSE START ===
[... Claude's complete response ...]
=== CLAUDE RESPONSE END ===

[2025-10-11 15:42:00] Task execution completed successfully

Examples

View recent logs:

/nights-watch logs

Follow logs in real-time:

/nights-watch logs -f

Use interactive log viewer:

# For more advanced viewing with filtering
${CLAUDE_PLUGIN_ROOT}/view-logs.sh

Implementation

${CLAUDE_PLUGIN_ROOT}/claude-nights-watch-manager.sh logs "$@"

Interactive Log Viewer

For advanced log viewing with filtering options, use the interactive viewer:

Read the full file on GitHub · 119 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. 9d ago First seen · 119 lines · 11 tokens per session scan A 58bf4e8439af

Subscribe to this mod's changes

logs is a command published in the GitHub repository aniketkarne/ClaudeNightsWatch (370 stars, last pushed 7mo ago), licensed MIT. It adds 11 tokens to every session and 745 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 2026-08-30.