# Send Terminal Killer to your agent
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
## Fast path
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
## Suggested prompts
### New install

```text
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete.
```
### Upgrade existing

```text
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run.
```
## Machine-readable fields
```json
{
  "schemaVersion": "1.0",
  "item": {
    "slug": "terminal-killer",
    "name": "Terminal Killer",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/cosperypf/terminal-killer",
    "canonicalUrl": "https://clawhub.ai/cosperypf/terminal-killer",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/terminal-killer",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=terminal-killer",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "clawhub.json",
      "references/EXAMPLES.md",
      "references/TESTING.md",
      "references/builtins/linux.txt"
    ],
    "downloadMode": "redirect",
    "sourceHealth": {
      "source": "tencent",
      "slug": "terminal-killer",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-04T02:45:34.408Z",
      "expiresAt": "2026-05-11T02:45:34.408Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=terminal-killer",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=terminal-killer",
        "contentDisposition": "attachment; filename=\"terminal-killer-1.2.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "terminal-killer"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/terminal-killer"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    }
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/terminal-killer",
    "downloadUrl": "https://openagent3.xyz/downloads/terminal-killer",
    "agentUrl": "https://openagent3.xyz/skills/terminal-killer/agent",
    "manifestUrl": "https://openagent3.xyz/skills/terminal-killer/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/terminal-killer/agent.md"
  }
}
```
## Documentation

### Terminal Killer

🚀 Smart command router that executes shell commands directly, bypassing LLM for instant terminal operations.

### Quick Start

Terminal Killer automatically activates when user input matches command patterns. No special syntax needed — just type commands naturally:

ls -la              # → Direct exec
git status          # → Direct exec  
npm install         # → Direct exec
"help me code"      # → LLM handles normally

### Detection Pipeline

User Input → Command Detector → Decision
                                      ├── Command → exec (direct)
                                      └── Task → LLM (normal)

### Environment Loading

Terminal Killer automatically loads your shell environment before executing commands:

Detects your shell (zsh, bash, etc.)
Sources init files (~/.zshrc, ~/.bash_profile, ~/.bashrc, etc.)
Inherits full PATH - including custom paths like Android SDK, Homebrew, etc.
Preserves environment variables - all your export VAR=value settings

This ensures commands like adb, kubectl, docker, etc. work exactly as they do in your terminal!

### Detection Rules (in order)

System Builtins - Check against OS-specific builtin commands
PATH Executables - Scan $PATH for matching executables
History Match - Compare against recent shell history
Command Pattern - Heuristic analysis (operators, paths, etc.)
Confidence Score - Combine signals for final decision

### 1. System Builtins

Checks input against known builtin commands for the current OS:

macOS/LinuxWindows (PowerShell)Windows (CMD)cd, pwd, lscd, pwd, lscd, dir, clsecho, catecho, catecho, typemkdir, rm, cpmkdir, rm, cpmkdir, del, copygrep, findgrep, findfindstrgit, npm, nodegit, npm, nodegit, npm, node

See references/builtins/ for complete lists.

### 2. PATH Executable Check

Scans $PATH directories to verify if the first word is an executable:

# Uses \`which\` (Unix) or \`Get-Command\` (PowerShell)
which <command>    # Returns path if exists

### 3. History Matching

Compares input against recent shell history (~/.zsh_history, ~/.bash_history, PowerShell history):

Exact match → High confidence
Similar prefix → Medium confidence
No match → Continue checking

### 4. Command Pattern Analysis

Heuristic scoring based on command characteristics:

PatternScoreExampleStarts with known command+3git statusContains shell operators+2\`lsContains path references+2cd ~/projectsContains flags/args+1npm install --saveContains $ variables+2echo $HOMEContains redirection+2cat file > outLooks like natural language-3"please help me"Contains question marks-2"how do I...?"

### 5. Confidence Threshold

Score >= 5  → EXECUTE (high confidence command)
Score 3-4   → ASK (uncertain, confirm with user)
Score < 3   → LLM (likely a task/request)

### Automatic Activation

Terminal Killer triggers automatically when:

User input starts with a verb-like word
Input is short (< 20 words typically)
No question words (what, how, why, etc.)

### Interactive Commands

Terminal Killer automatically detects and handles interactive shell commands:

Detected Patterns:

adb shell - Opens new terminal with adb shell
ssh user@host - Opens SSH session in new window
docker exec -it container bash - Opens container shell
mysql -u root -p - Opens MySQL client
python, node, bash - Opens REPL in new window

Behavior:

✅ Automatically opens new Terminal window (macOS)
✅ Loads your full shell environment (~/.zshrc, etc.)
✅ Keeps main session free for other tasks

### Manual Override

Force command execution:

!ls -la          # Force exec even if uncertain

Force LLM handling:

?? explain git   # Force LLM even if looks like command

### Dangerous Command Detection

Automatically flags potentially dangerous operations:

rm -rf / or similar destructive patterns
sudo commands (requires explicit approval)
dd, mkfs, chmod 777
Network operations to suspicious hosts
Commands modifying system files

### Approval Workflow

Dangerous command detected!

Command: rm -rf ./important-folder
Risk: HIGH - Recursive delete

[Approve] [Deny] [Edit]

### Audit Logging

All executed commands are logged to:

~/.openclaw/logs/terminal-killer.log

Log format:

{
  "timestamp": "2026-02-28T12:00:00Z",
  "command": "ls -la",
  "confidence": 8,
  "execution_time_ms": 45,
  "output_lines": 12,
  "status": "success"
}

### Settings

Add to your OpenClaw config:

terminal-killer:
  enabled: true
  confidence_threshold: 5
  require_approval_for:
    - "rm -rf"
    - "sudo"
    - "dd"
    - "mkfs"
  log_executions: true
  max_history_check: 100  # How many history entries to check

### Platform Detection

Automatically detects OS and adjusts detection rules:

# Auto-detected at runtime
uname -s  # Darwin, Linux, etc.

### Core Script

See scripts/detect-command.js for the main detection logic.

### Helper Scripts

scripts/check-path.js - Verify executable in PATH
scripts/check-history.js - Match against shell history
scripts/score-command.js - Calculate confidence score
scripts/safety-check.js - Detect dangerous patterns

### Testing

See references/TESTING.md for comprehensive test guide.

Quick test:

# Run the test suite
node scripts/test-detector.js

# Test specific commands
node scripts/detect-command.js "ls -la"
node scripts/detect-command.js "help me write code"

### Limitations

Requires shell access (won't work in sandboxed environments)
History check needs read access to shell history files
Windows support requires PowerShell or WSL for full functionality
Some commands may have false positives (natural language that looks like commands)

### Contributing

To add new builtin commands for your platform:

Edit references/builtins/<platform>.txt
Test with scripts/test-detector.js
Submit PR with platform verification

### 👤 About the Creator

Author: Cosper
Contact: cosperypf@163.com
License: MIT

### 📬 Get in Touch

Interested in this skill? Have suggestions, bug reports, or want to collaborate?

📧 Email: cosperypf@163.com
💡 Suggestions: Always welcome!
🐛 Bug Reports: Please include platform, OpenClaw version, and example inputs
🤝 Collaboration: Open to contributions and improvements

### 🙏 Acknowledgments

Built for the OpenClaw community. Thanks to everyone contributing to the ecosystem!

### v1.1.0 (2026-02-28)

🎯 Core Improvements:

✅ Faithful Command Execution

Commands are executed exactly as input
No modifications, no optimizations, no additions
Raw output preserved (including progress bars, special characters, etc.)



🪟 Interactive Shell Detection

Automatically detects interactive commands (adb shell, ssh, docker exec -it, etc.)
Opens new Terminal window for interactive sessions
Keeps main session free for other tasks
Loads full shell environment (~/.zshrc, etc.)



📜 Long Output Handling

Detects output longer than 2000 bytes
Shows 200-character preview
Prompts user to open in new Terminal window
Prevents interface rendering issues with long content

📦 Files Updated:

scripts/index.js - Long output detection + interactive command handling
scripts/interactive.js - New Terminal window opener
SKILL.md - Updated documentation
README.md - Usage examples
clawhub.json - Version bump to 1.1.0

### v1.0.0 (2026-02-28)

Initial Release:

Smart command detection (system builtins, PATH, history, patterns)
Cross-platform support (macOS/Linux/Windows)
Environment variable loading (~/.zshrc, etc.)
Dangerous command detection
Confidence scoring system

Version: 1.1.0
Created: 2026-02-28
Last Updated: 2026-02-28
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: cosperypf
- Version: 1.2.0
## Source health
- Status: healthy
- Item download looks usable.
- Yavira can redirect you to the upstream package for this item.
- Health scope: item
- Reason: direct_download_ok
- Checked at: 2026-05-04T02:45:34.408Z
- Expires at: 2026-05-11T02:45:34.408Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/terminal-killer)
- [Send to Agent page](https://openagent3.xyz/skills/terminal-killer/agent)
- [JSON manifest](https://openagent3.xyz/skills/terminal-killer/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/terminal-killer/agent.md)
- [Download page](https://openagent3.xyz/downloads/terminal-killer)