free-models

A set of instructions for assigning suitable delegated work to free model services, such as free OpenRouter variants or the OpenCode Zen free tier.

In plain words
What is it for?
Use it when delegating work on a low budget or with no spending, while considering tool support, privacy, rate limits, and task risk.
Why use it?
It helps reduce model costs while checking that the chosen service can use tools and avoids silently switching to a paid service when it fails.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/vironnimo/vbot/free-models
Any agent
npx skills add Vironnimo/vbot --skill free-models
Clone the repo
git clone --depth 1 https://github.com/Vironnimo/vbot

Made for: Claude Code, Codex.

Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 995 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00123 $0.00995
Opus 5 $0.00062 $0.00498
Sonnet 5 $0.00025 $0.00199
Haiku 4.5 $0.00012 $0.00100

Measured 2d ago against content hash d6b422978897, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

free-models scanned grade A with 0 findings 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 2d ago.

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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

resources/skills/free-models/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Free Models

Free capacity serves delegated work. You route suitable Sub-Agent Runs to free Models through the subagent Tool's per-Run model override (<provider>/<model-id>, applies only to that Run). You never change the calling Agent's own Model, any stored configuration, or a Project default through this skill, and never do so silently.

Non-negotiable rules

  1. Tools gate. A Sub-Agent without tool calling is broken, not cheap. Propose only Models whose catalog record confirms tool support (vbot model show <id>), and only ids that appear in vbot model list — a configured, usable Connection.
  2. No silent paid fallback. When a free Model fails or returns unusable output, rotate to another free Model, wait out rate limits, or report the gap. Moving the work to a paid Model spends money and requires the user's explicit consent first.
  3. Quality boundary. Ask before routing security-sensitive, architectural, irreversible, or otherwise high-stakes work to a weaker Model. Saving cents is never worth silently degrading an outcome the user cares about.
  4. Privacy boundary. Free tiers are often paid in data — several free endpoints log inputs or train on them. Never put credentials, secrets, or tokens into delegated task text. Flag sensitive content to the user and prefer zero-retention, paid, or local alternatives for it.
  5. Rate limits are real. OpenRouter free variants allow 20 requests per minute, 50 requests per day (raised to 1000 once the account has purchased at least $10 in credits, ever); expect HTTP 429 as routine. Spread siblings across different free Models instead of stacking parallel Runs on one, and treat exhausted quotas as a reason to defer work, not to fall back to paid.
  6. Verify before trusting. The curated list in references/free-models.md is a dated hint. Free lineups churn weekly — confirm current free status and availability live before relying on any entry (recipe in that file).

Read the full file on GitHub · 67 lines

Files

What ships with it

2 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.

  1. 2d ago First seen · 67 lines · 123 tokens per session scan A d6b422978897

Subscribe to this mod's changes

free-models is a skill published in the GitHub repository Vironnimo/vbot (1 stars, last pushed 3d ago), licensed Apache-2.0. It adds 123 tokens to every session and 995 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

openclaw

Use when setting up a multi-channel personal AI assistant gateway bridging chat platforms (Telegram, Discord, WhatsApp, WeChat) with LLM backends. OpenClaw: multi-channel AI assistant gateway for unified personal AI access.

znlgis/opengis-skills · 50 tokens

feishu-codex-linker

Install, configure, repair, update, or rebind the Codex Bridge core with the Feishu pack after the user installs this skill. Use when the user wants Codex to take over bridge setup with minimal user action, only interrupting for unavoidable external steps like providing a Feishu app id/app secret or messaging the…

InDreamer/telegram-codex-bridge · 77 tokens

copilotkit-develop

Use when building AI-powered features with CopilotKit v2 -- adding chat interfaces, registering frontend tools, sharing application context with agents, handling agent interrupts, and working with the CopilotKit runtime.

CopilotKit/CopilotKit · 46 tokens

harness-creator

Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…

walkinglabs/learn-harness-engineering · 142 tokens

hive.worker-delegation

Concrete patterns for breaking colony work into parallel worker jobs via runplaybook — when fan-out helps, how to model the goal as a tracker table, write the worker skill, author the playbook, pilot, and let convergence retry/resume the gap.

aden-hive/hive · 58 tokens

review-agents-md

Audit Dograh AGENTS.md files for drift against the live repo and for bad scope boundaries between parent and child docs. Use when the user asks to review existing AGENTS files, identify stale guidance, decide whether a subtree needs its own AGENTS.md, or update the AGENTS.md hierarchy under the repo root, api/, or ui/.

dograh-hq/dograh · 82 tokens