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.
npx agentmods add commands/aniketkarne/claudenightswatch/setupgit clone --depth 1 https://github.com/aniketkarne/ClaudeNightsWatchWrote 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.
[](https://agentmods.dev/commands/aniketkarne/claudenightswatch/setup)<a href="https://agentmods.dev/commands/aniketkarne/claudenightswatch/setup"><img src="https://agentmods.dev/badge/commands/aniketkarne/claudenightswatch/setup.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00008 | $0.00774 |
| Opus 5 | $0.00004 | $0.00387 |
| Sonnet 5 | $0.00002 | $0.00155 |
| Haiku 4.5 | $0.00001 | $0.00077 |
Grade A, and why
setup 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nights Watch Setup Wizard
Launch the interactive setup wizard to configure Claude Nights Watch for the first time or modify existing configuration.
Usage
/nights-watch setup
Setup Process
The wizard guides you through:
1. Prerequisites Check
- ✓ Verify Claude CLI is installed
- ✓ Check for ccusage (for accurate timing)
- ✓ Confirm required permissions
2. Task Configuration
- Create or edit
task.mdfile - Enter task instructions
- Review and modify as needed
3. Safety Rules Configuration
- Create or edit
rules.mdfile - Choose from default safety templates
- Customize rules for your project
4. Daemon Configuration
- Choose to start daemon immediately or later
- Optionally schedule a start time
- Configure monitoring preferences
5. Summary
- Review all configuration
- Display available commands
- Optionally start daemon
Interactive Prompts
================================
Claude Nights Watch Setup
================================
Checking prerequisites...
✓ Claude CLI found
! ccusage not found (will use time-based checking)
To install ccusage: npm install -g ccusage
=== Task Configuration ===
task.md already exists
Do you want to view/edit it? (y/n)
=== Safety Rules Configuration ===
Do you want to create safety rules? (recommended) (y/n)
=== Daemon Configuration ===
Do you want to start the daemon after setup? (y/n)
Do you want to schedule a start time? (y/n)
Enter start time (HH:MM for today, or YYYY-MM-DD HH:MM):
=== Setup Complete ===
✓ Task file: /path/to/task.md
✓ Rules file: /path/to/rules.md
✓ Manager: /path/to/claude-nights-watch-manager.sh
Available commands:
/nights-watch start - Start the daemon
/nights-watch stop - Stop the daemon
/nights-watch status - Check daemon status
/nights-watch logs - View logs
/nights-watch task - View current task
Starting daemon...
What Gets Created
Files Created
task.md- Your task instructions (if doesn't exist)rules.md- Safety rules (optional, if requested)logs/- Directory for daemon logs (on first start)
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.
- 5d ago First seen · 131 lines · 8 tokens per session scan A 47fb7348c647
setup is a command published in the GitHub repository aniketkarne/ClaudeNightsWatch (370 stars, last pushed 7mo ago), licensed MIT. It adds 8 tokens to every session and 774 once invoked, about $0.0000 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.