Free Worker Dispatch

Route tasks to free AI models via OpenRouter to save money. Use when the agent needs to delegate content writing, research, code generation, or other tasks t...

Security Scan

The skill's code and instructions consistently implement routing tasks to free models via OpenRouter and only require a single OpenRouter API key and python3; nothing requests unrelated credentials or installs arbitrary software.

Purpose & Capability

The name/description (route tasks to free models via OpenRouter) matches the actual requirements (python3 and OPENROUTER_API_KEY) and the script calls openrouter.ai. No unrelated cloud credentials or unrelated binaries are requested.

Instruction Scope

Runtime instructions tell the agent to run the included Python script and use the OPENROUTER_API_KEY. The script only reads provided prompts/tasks and optional output paths; it does not enumerate or exfiltrate other system files. Minor doc/code mismatches: SKILL.md and the script differ slightly in the model table and the SKILL.md suggests general auto-routing while the script's MODEL_MAP differs for some types. The script prints an error suggesting 'credentials.txt' as an alternative place to set the key, but there is no code that reads credentials.txt.

Install Mechanism

No install spec is provided (instruction-only with a single Python script). That is low-risk: nothing is downloaded or written to disk during installation beyond what the user runs.

Credentials

Only OPENROUTER_API_KEY (and python3) are required, which is proportional for a tool that calls OpenRouter. The script does not request other secrets or config paths and includes checks to prevent writing to common sensitive paths (e.g., .ssh, .aws, .env).

Persistence & Privilege

The skill is not always-enabled and is user-invocable. It does not modify other skills or system configuration. It can be invoked autonomously only per platform default, which is expected for skills.

Assessment

This skill appears coherent and limited in scope, but before installing: (1) Understand that your OPENROUTER_API_KEY will be sent to openrouter.ai (this is necessary for the tool to function) — only provide a key you trust to share with that service. (2) Review the model list and MODEL_MAP in the script vs the README if you rely on specific models (there are minor mismatches). (3) The script will write output files but refuses sensitive paths; still double-check any output file names you provide. (4) Because free models can hallucinate, always review model output before publishing. (5) If you are concerned about key leakage, create/limit a dedicated OpenRouter key and rotate it if needed.

Delegate tasks to free AI models via OpenRouter. Save your expensive primary model for strategy and quality review — let free models handle the grunt work.

Why This Exists

Running everything through Claude Opus or GPT-4 costs real money. Free models on OpenRouter handle most content, research, and coding tasks perfectly well. This skill routes tasks intelligently, saving agents from surprise bills.

Available Free Models

Model	Best For	Context
stepfun/step-3.5-flash:free	Research, analysis, brainstorming	128K
arcee-ai/trinity-large-preview:free	SEO copy, blog posts, marketing	128K
openrouter/free	Auto-route to best available free model	Varies

Commands

Dispatch a task to a free model

python3 {baseDir}/scripts/dispatch.py task --prompt "Write a blog post about freelance copywriting rates in 2026" --model "arcee-ai/trinity-large-preview:free"

Dispatch with auto-model selection

python3 {baseDir}/scripts/dispatch.py task --prompt "Research the top 10 Notion templates for freelancers" --type research

List available free models

python3 {baseDir}/scripts/dispatch.py models

Check model status (is it up?)

python3 {baseDir}/scripts/dispatch.py status --model "stepfun/step-3.5-flash:free"

Dispatch with output to file

python3 {baseDir}/scripts/dispatch.py task --prompt "Write an email newsletter about AI tools" --type content --output newsletter-draft.md

Batch dispatch (multiple tasks)

python3 {baseDir}/scripts/dispatch.py batch --file tasks.json

The tasks.json format:

[
  {"prompt": "Write a product description", "type": "content"},
  {"prompt": "Research competitor pricing", "type": "research"},
  {"prompt": "Generate a Python script for...", "type": "code"}
]

Task Types

The --type flag auto-selects the best free model:

Type	Model	Why
research	stepfun/step-3.5-flash:free	Fast, good at analysis
content	arcee-ai/trinity-large-preview:free	Strong at writing
code	openrouter/free	Auto-routes to best coder
general	openrouter/free	Let OpenRouter decide

Output

Results are printed to stdout by default. Use --output <file> to save to a file. Use --json for structured JSON output including model used, tokens, and timing.

Tips

• Always review worker output before publishing — free models hallucinate
• Use --type for best model matching instead of specifying models directly
• Batch dispatch is faster for multiple independent tasks
• If a model is down, the script falls back to openrouter/free