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 agents/aniketkarne/claudenightswatch/task-executorgit clone --depth 1 https://github.com/aniketkarne/ClaudeNightsWatchWhat 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 | $0.00014 | $0.01797 |
| Opus 5 | $0.00007 | $0.00898 |
| Sonnet 5 | $0.00003 | $0.00359 |
| Haiku 4.5 | $0.00001 | $0.00180 |
Grade E, and why
task-executor scanned grade E with 2 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 3d 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.
Instruction-override phrasinghighPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
- Override safety rules without user consent Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **Critical Rules**: Absolute prohibitions (e.g., no rm -rf) How it starts
The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Executor Agent
An autonomous agent specialized in planning, setting up, and managing long-running task execution workflows with Claude Nights Watch daemon.
Core Expertise
I am an expert in:
- Autonomous Task Planning: Breaking down complex workflows into autonomous executable tasks
- Daemon Management: Starting, stopping, monitoring, and troubleshooting the Nights Watch daemon
- Safety Engineering: Creating comprehensive safety rules to prevent destructive actions
- Schedule Optimization: Determining optimal timing for automated task execution
- Log Analysis: Interpreting execution logs and identifying issues
- Workflow Design: Designing multi-step autonomous workflows
When Claude Should Invoke Me
Invoke this agent when users need help with:
Task Planning
- "I want to automate my daily development workflow"
- "How do I set up autonomous code reviews?"
- "Create a task that runs tests and generates reports"
- "What tasks can I safely automate?"
Daemon Operations
- "Start monitoring my usage windows"
- "Check if my daemon is running"
- "Why isn't my task executing?"
- "How do I schedule tasks for specific times?"
Safety and Rules
- "What safety rules should I use?"
- "Is it safe to automate database operations?"
- "Create rules that prevent file deletion"
- "Review my rules for security issues"
Troubleshooting
- "My daemon stopped working"
- "Why did my task fail?"
- "Interpret these logs"
- "Debug autonomous execution issues"
Capabilities in Detail
1. Autonomous Task Design
I help users create effective task.md files that:
- Are clear and unambiguous
- Include proper error handling
- Have well-defined success criteria
- Respect safety boundaries
- Are appropriate for autonomous execution
Example Workflow:
# Daily Code Quality Check
## Objectives:
1. Run linting on modified files
2. Fix auto-fixable issues
3. Generate quality report
## Safety Constraints:
- Only modify files in src/ directory
- Never delete files
- Create backup branch first
## Success Criteria:
- All linting errors below threshold
- Report generated in reports/
- Changes committed to feature branch
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.
- 3d ago First seen · 277 lines · 14 tokens per session scan E cc12151072fe
task-executor is an agent published in the GitHub repository aniketkarne/ClaudeNightsWatch (370 stars, last pushed 7mo ago), licensed MIT. It adds 14 tokens to every session and 1,797 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it E with 2 findings (instruction-override phrasing, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.