Real Skill packageSource verifiedClawHub registry

model-inventory

Scan the machine for installed AI coding CLIs (claude, codex, gemini, copilot, opencode, ollama), detect whether each account is actually active and which models are usable, and cache the result to ~/.claude/model-inventory.json with role→model routing chains (planner/coder/scout/reviewer/fixer) that goal-runner and autopilot consume to pick the best available model per sub-agent while staying cost-efficient. Three evidence tiers — installed (binary found), likely-authenticated (zero-token credential heuristics),…

Identity and source

Publisher attributionDennis Rongoregistry owner unverified by skillvetai
Functional categorySoftware Developmentautomatically inferred · 60% rule confidence
Package forminstruction with code4 recorded files
Canonical sourceClawHub registryclawhub:dennisrongo:model-inventory
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 · 8/16/2026.claude/skills/model-inventory

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 · 8/16/2026.agents/skills/model-inventory

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 · 8/16/2026skills/model-inventory

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 @dennisrongo/model-inventory
clawhub inspect @dennisrongo/model-inventory --version 1.0.0

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
4 / 4 inspected as text
Checked
8/16/2026, 9:38:28 PM
Scanner
0.1.3
Policy
1.0.3
3 inferred permission indicators
  • network access — automatically inferred
  • filesystem write — automatically inferred
  • credential access — automatically inferred
1 dependency and API indicators
  • api: clawhub.ai
External clawhub result: clean

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
8/16/2026, 8:58:22 PM
Release binding
Matches this record
  • vt: clean
  • skillspector: suspicious
  • llm: clean

Recorded files

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

Package content hashsha256:0508de563dd88cc790c0460349c8b88c6d0556e606e49e1ed5d9249811c288f3
Show up to 4 recorded paths
  • references/cli-registry.md
  • scripts/scan.sh
  • skill-card.md
  • SKILL.md

Source changelog

Initial release of the model-inventory skill, providing structured discovery and verification of AI CLI model access for downstream agent-task routing. - Scans for installed AI coding CLIs (e.g., claude, codex, gemini, copilot, opencode, ollama) and detects their presence and authentication status using three evidence tiers. - Probes each CLI for live model access to distinguish between installed, likely-authenticated, and actually usable (verified) models. - Constructs and caches a routing table (role→model chains) and CLI inventory in ~/.claude/model-inventory.json for other skills to consume. - Designed for explicit, on-demand inventory refresh requests (e.g., “scan available models”, “refresh the model inventory”); not for mid-task model selection. - Enforcement of evidence rigor: only models proven by live probe are marked as verified; credential presence alone never counts as veri…