SKILLEMALL.ai
GitHub ↗ RU Sign in

BD iblai-router

Cost-optimizing model router for OpenClaw. Automatically routes each request to the cheapest capable Claude model (Haiku/Sonnet/Opus) using weighted scoring. Use when setting up smart model routing, reducing API costs, or configuring multi-tier LLM routing. Supports Anthropic models directly and OpenAI/Google models via OpenRouter.

modbender/skill-library-mcp Agent Skills author: modbender MIT 6 files · 2 scripts body ≈ 689 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Cost-optimizing model router for OpenClaw.

As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

IntegrationAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
84/100
safety, quality, tests
Safety 60%
83
Quality 40%
85
Run on models
none yet
Process rating
D
46/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

    For the model run — optional
    • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 5

    ✓ No critical or high findings

    Medium and low: 5
    • medium Dangerous commands cmd-privilege README.md:135
      Privilege escalation / world-writable permissions
      sudo tee /etc/systemd/system/iblai-router.service > /dev/null << EOF
    • medium Dangerous commands cmd-privilege scripts/install.sh:40
      Privilege escalation / world-writable permissions
      sudo tee /etc/systemd/system/$SERVICE_NAME.service > /dev/null << EOF
    • medium Dangerous commands cmd-privilege scripts/uninstall.sh:21
      Privilege escalation / world-writable permissions
      sudo rm "/etc/systemd/system/$SERVICE_NAME.service"
    • low Dangerous commands cmd-background-process README.md:156
      Starts a background / autostarted process
      sudo systemctl enable --now iblai-router
    • low Dangerous commands cmd-background-process scripts/install.sh:62
      Starts a background / autostarted process
      sudo systemctl enable --now "$SERVICE_NAME"

    Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 46/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Failures and branches. Linear process with no failure handling
    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 6 mutating operations with no state check
    • 40Consistency. Frontmatter name (iblai-router) differs from the folder (iblai-openclaw-router)
    • 100Tools and files. No external tools needed
    • 100Steps. 6 steps
    • 100Execution cost. Instruction body is 689 tokens

    Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

    Quality signals

    • +5Description has no quoted example phrases that should trigger the skill
    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • -2localhost URLs: will not work for another user
    • +1No license
    • +2Single-language instructions
    • +3Description length 333: enough signal without eating the budget
    • +4Structure: 9 headings
    • +3Step-by-step instructions: 6 items
    • +4Has examples (5 code blocks)
    • +3All 2 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.