Model Alias Append

Automatically appends the model alias to the end of every response with integrated hook functionality and configuration change detection. Use when transparency about which model generated each response is needed. Use when: providing model transparency, tracking which model generated responses, monitoring configuration changes, or ensuring response attribution.

MIT-0 · Free to use, modify, and redistribute. No attribution required.
3 · 1.9k · 2 current installs · 2 all-time installs
MIT-0
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description claim: append model alias and detect config changes. The code implements alias extraction, response modification, config polling, and a script to enable/disable a response hook — all directly related to the stated purpose.
Instruction Scope
SKILL.md and code instruct the agent to read ~/.openclaw/openclaw.json (and similar paths) and modify responses. The manage-hook script also writes into the user's openclaw.json to enable/disable the hook. That behavior is consistent with enabling the hook but is a scope note because it modifies a global config file.
Install Mechanism
No remote downloads or install spec; this is a local package with source files bundled. There are no npm dependencies or external installers referenced, so nothing is fetched from untrusted URLs at runtime.
Credentials
The skill requests no environment variables or credentials. It reads the local OpenClaw config file (which is reasonable to determine aliases); it does not transmit data externally or require unrelated secrets.
Persistence & Privilege
always is false and autonomous invocation is allowed by default (normal). The skill sets up a periodic timer to poll the config and provides methods that run a local script to modify ~/.openclaw/openclaw.json to enable/disable the hook. Modifying the global config is justified for enabling the hook but is a privileged action the user should be aware of.
Assessment
This skill appears to do what it says: it reads your OpenClaw configuration to map model IDs to aliases, appends aliases to responses, and watches the config for changes. Before installing or enabling the hook, consider: 1) Back up your ~/.openclaw/openclaw.json — the manage-hook script will write to it to toggle the response-alias-injector entry. 2) Review your openclaw.json for any sensitive fields (the skill reads that file) and ensure you're comfortable with a skill reading it. 3) The skill does not make network requests or request secrets; however, only install from a source you trust (the package metadata points to a GitHub repo). 4) If you prefer not to have any package modify your global config, avoid calling the enable/disable hook methods — you can enable the hook manually in your config instead. Overall this package is internally consistent with its description.

Like a lobster shell, security has layers — review code before you run it.

Current versionv1.0.2
Download zip
latestvk9784vd9m6b8gjpgcgbmqap3j980awt0

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

SKILL.md

Model Alias Append Skill

Automatically appends model alias to responses with configuration change detection

Model Alias Example

Key Features

  • 🔍 Automatic Detection - Identifies the model used for each response
  • 🏷️ Alias Appending - Adds model alias from openclaw config agents.defaults.models.{yourModelDict}.alias format like the config below
"agents": {
  "defaults": {
    "model": {
      "primary": "gemma3:27b-local",
      "fallbacks": [ "qwen" ]
    },
    "models": {
      "ollama-local/gemma3:27b": {
        "alias": "gemma3:27b-local"
      },
      "qwen-portal/coder-model": {
        "alias": "qwen"
      }
    }
  }
}
  • 🔄 Real-time Monitoring - Watches for configuration changes
  • 📢 Update Notifications - Shows when config changes occur
  • 🛡️ Format Preservation - Maintains reply tags and formatting

Install

npx clawhub@latest install model-alias-append

How It Works

  1. Intercepts responses before sending
  2. Determines which model generated the response
  3. Appends the appropriate model alias
  4. Shows update notices when configuration changes

Setup

No additional configuration needed - reads from your existing openclaw.json

Output Example

Your response content...

[Model alias configuration updated] // This line will not appear until openclaw.json modified

gemma3:27b-local

Files

8 total
Select a file
Select a file to preview.

Comments

Loading comments…