Real Skill packageSource verifiedClawHub registry

free-tier-ai-router

Quota-aware LLM router that squeezes maximum usable AI out of free-tier API keys across Gemini, Mistral, OpenRouter, Kilo and Cerebras plus any OpenAI-compatible endpoint (including local Ollama/llama.cpp/vLLM). Probes every model on every key, measures real quality and real published rate limits, then routes each request to the cheapest model that can do the job — spending abundant capacity first and reserving scarce daily quota for when it is actually needed. Persists cooldowns to disk so a 429 discovered in one…

Identity and source

Publisher attributionorionshaowswmwregistry owner unverified by skillvetai
Functional categorySoftware Developmentautomatically inferred · 53% rule confidence
Package forminstruction with code30 recorded files
Canonical sourceClawHub registryclawhub:orionshaowswmw:free-tier-ai-router
Open canonical source ↗

Platform declarations

These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.

OpenClawnative officialProvenance: registry distribution

Independent structural checks

These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.

Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 9/15/2026.claude/skills/free-tier-ai-router

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 9/15/2026.agents/skills/free-tier-ai-router

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenClawpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 9/15/2026skills/free-tier-ai-router

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

Installation and inspection

This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.

clawhub install @orionshaowswmw/free-tier-ai-router
clawhub inspect @orionshaowswmw/free-tier-ai-router --version 2.5.4

Security evidence

SkillVetAI static result: no findings detected

This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.

Status
completed
Coverage
full text content
Files
30 / 30 inspected as text
Checked
9/15/2026, 5:09:15 PM
Scanner
0.1.3
Policy
1.0.3
4 inferred permission indicators
  • shell execution — automatically inferred
  • network access — automatically inferred
  • filesystem read — automatically inferred
  • filesystem write — automatically inferred
15 dependency and API indicators
  • api: aistudio.google.com
  • api: api.cerebras.ai
  • api: api.cohere.com
  • api: api.groq.com
  • api: api.kilo.ai
  • api: api.llm7.io
  • api: api.mistral.ai
  • api: app.kilo.ai
  • api: clawhub.ai
  • api: console.mistral.ai
  • api: generativelanguage.googleapis.com
  • api: hub.openclaw.ai
  • api: json-schema.org
  • api: openrouter.ai
  • api: router.huggingface.co
External clawhub result: suspicious

This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.

Evidence checked
9/14/2026, 9:25:21 PM
Release binding
Matches this record
  • skillspector: suspicious
  • llm: suspicious

Recorded files

The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.

Package content hashsha256:5a8a92ae8f5fe6f5c68d86f44ad4221487d9cf52e040499bea84ab0fe4fbe90e
Show up to 30 recorded paths
  • _meta.json
  • AGENT_DISCOVERY.md
  • get-ai-router.sh
  • health.json
  • install.sh
  • integrate.sh
  • PROBE.md
  • probe.py
  • quality.json
  • quality.py
  • ratelimit.py
  • ratelimits.json
  • README.md
  • references/history.md
  • references/measurements.md
  • references/model-tags.json
  • references/model-tags.md
  • references/providers.md
  • results.json
  • router_fixed.json
  • router.py
  • schema/answer.v1.schema.json
  • schema/learn.v1.schema.json
  • schema/plan.v1.schema.json
  • schema/providers.config.schema.json
  • schema/status.v1.schema.json
  • scripts/mock_provider.py
  • scripts/selftest.sh
  • skill-card.md
  • SKILL.md

Source changelog

v2.5.4: model-tags canonicalization — owner-supplied tag set shipped (24 primary: redundant llama-3.3-70b-versatile alias merged into single llama-3.3-70b Groq·Cerebras entry; 8 secondary; 15-tag taxonomy). Distributed re-audit (arena agent + 5 live cloud models across Groq/Cohere/Gemini/llm7/HuggingFace; 3 known-flaky providers documented) confirmed all 32 entries correct; 1 advisory recorded (Mistral Small 4 119B-2603 MoE variant per HF card). No code changes.

Release security diff

mediumCompared fixed releases 2.4.3 and 2.5.4; 0 finding and 0 permission indicators were added.

Both fixed releases were scanned under the current scanner and policy, so finding, permission and dependency changes are available.

Change reasons and limitations
  • dependency surface changed
  • file surface changed
  • content hash changed

Observed release history

These older immutable releases were observed by prior successful syncs. They remain recorded when a newer release becomes current.

2.4.39/7/2026sha256:7eb92cb27b04605b03409a2822c93413c9d28bda29afbfa1df3e1ba0c00ffb29
2.4.29/6/2026sha256:9d3ace3b01b1d958b0326ee1b4fd47672b6f2f09d79fb2f95047a308dd6f95dd
2.4.09/6/2026sha256:36dab893f747a90a71937e0b5651920880e0dfbebb14dd7facb69cbace27a2a2
2.2.98/25/2026sha256:e998e159cf57b38c580b0f9bc4c93aee4fc6578d74062528173f7515d9fcb448