A toolkit for finding free cloud language models through OpenRouter and Ollama, services that provide access to models from different providers. It can inspect models, compare them with a catalogue, test whether they respond, and update models.json.

Use it to scan free models, fetch popular models from a leaderboard, inspect one model, test model availability, or add models manually. It supports updating the repository’s models.json file.

It reduces the manual work of discovering available free models and checking whether they are live. It also keeps the repository’s model list current when you choose to write the results.

model-scout — Skill for Claude Code by aksika

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add aksika/abtars --skill model-scout

Clone the repo

git clone --depth 1 https://github.com/aksika/abtars

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/aksika/abtars/model-scout.svg)](https://agentmods.dev/skills/aksika/abtars/model-scout)

Your own site

<a href="https://agentmods.dev/skills/aksika/abtars/model-scout"><img src="https://agentmods.dev/badge/skills/aksika/abtars/model-scout.svg" alt="Measured on agentmods" height="20"></a>

Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,011 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Rogue Agent · line 26
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
medium Data Exfiltration · line 114
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00018	$0.01011
Opus 5	$0.00009	$0.00505
Sonnet 5	$0.00004	$0.00202
Haiku 4.5	$0.00002	$0.00101

Measured 7d ago against content hash 6361e19d7dc1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

model-scout scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scout-add-model.py, scout-leaderboard.py, scout-ollama.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s https://openrouter.ai/api/v1/chat/completions \

templates/skills/model-scout/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Model Scout

Scout OpenRouter models — free tier, leaderboard top N, single model inspection.

Scripts

scout-openrouter.py — free model scan, single model inspection, leaderboard fetch
scout-leaderboard.py — dedicated leaderboard fetcher (top N by popularity)
scout-ollama.py — Ollama cloud models
scout-add-model.py — manual model addition

Usage

1. Scan free models (original behavior)

# List free models vs catalog
python3 {baseDir}/scout-openrouter.py

# List + liveness test + write status to models.json
python3 {baseDir}/scout-openrouter.py --test

2. Fetch leaderboard top N and add to models.json

# Print top 20 (no changes)
python3 {baseDir}/scout-leaderboard.py 20

# Add/update top 20 in models.json (no liveness test)
python3 {baseDir}/scout-leaderboard.py 20 --update

# Test each model + update
python3 {baseDir}/scout-leaderboard.py 20 --test

Also available via scout-openrouter.py:

python3 {baseDir}/scout-openrouter.py --leaderboard 20

3. Inspect + test a single model

python3 {baseDir}/scout-openrouter.py --model tencent/hy3:free

This fetches model metadata from /api/v1/models/{id} and provider endpoints from /api/v1/models/{id}/endpoints, tests liveness, and updates models.json.

4. Ollama cloud models

python3 {baseDir}/scout-ollama.py

What the scripts store

Each model entry in models.json gets:

contextWindow, maxOutput — from API context_length and top_provider.max_completion_tokens
rank — 1 (≥500K ctx), 2 (≥200K), 3 (smaller)
cost — per token, raw OpenRouter pricing (from pricing.prompt / pricing.completion). Accurate for calculations; picker display converts to $/1M via the display field derived in transport-config.ts.
transports — ["openrouter"]
status — "alive" or "dead" (from liveness test)
providers — dict of provider_name → {status, uptime_30m, latency_p50, throughput_p50, quant, max_completion_tokens}
validatedAt — ISO date

Read the full file on GitHub · 124 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

7d ago First seen · 124 lines · 18 tokens per session scan A 6361e19d7dc1

Subscribe to this mod's changes

model-scout is a skill published in the GitHub repository aksika/abtars (9 stars, last pushed 3d ago), licensed Apache-2.0. It adds 18 tokens to every session and 1,011 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Data and AI agent-security agent-swarm agentic-ai ai-agents ai-assistant ai-framework

world-model-diagnostic

Twenty-minute diagnostic mapping a team to a world-model paradigm (vector DB, structured ontology, signal-fidelity). Use when you say "run the world model diagnostic", "audit our world model", "which world model architecture fits us", or "audit where we automate judgment". Use for AI readiness assessments and…

rjmurillo/ai-agents · 94 tokens

benchmark-models

Cross-model benchmark. Runs one prompt or skill through Claude, GPT (Codex CLI), and Gemini side by side and compares latency, tokens, cost, tool calls, and optionally output quality via an Anthropic-API judge. Answers "which model is actually best for this skill?" with data. Use when you say "benchmark models"…

rjmurillo/ai-agents · 104 tokens

model-scout