ai-model-platform

How AI/model features should be configured, called, tuned, gated and cost-tracked in any app.

IndexedLicense unknown

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/automate-anything-ai-model-platform

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

How AI/model features should be configured, called, tuned, gated and cost-tracked in any app. Covers the feature_key contract (code defaults + a live tunable row + one telemetry stream + an optional billing path), keeping prompt/model/pricing as DATA not constants, the single wrapper every model call goes through, the connect-then-activate lifecycle with a visible "needs attention" queue, the two billing modes (billed per use vs platform-absorbed), the spend gate and 402 out-of-credit flow, usage rows and the billing job that debits a ledger, attribution for crons, kill switches, error classes, model slots with fallback legs, abuse caps for free features, provisioning provider keys by API, and the anti-patterns that silently lose money or telemetry. This is a pattern to BUILD per repository. Read it BEFORE building any feature that calls a model API, before adding a feature key, before wiring a prompt or a model choice, before designing the settings page that tunes them, and before touching AI billing. Use when the user mentions AI features, model calls, OpenAI, Anthropic, Claude, GPT, prompts, feature keys, token cost, model settings, AI usage tracking, AI credits, insufficient funds, a 402, spend limits, "which model", "what did AI cost us", or connecting/validating a provider key. For the agent architecture built on top of this, read `internal-ai-agent-architecture`.

Use cases: documents, backend, data, agent-building

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools: No tools found
Secrets: None asked for
Install scripts: None found

Network hosts it talks to 1

codeload.github.com · found in install command

Files it touches

~/.claude/skills/ai-model-platform

What's inside

Skill name: ai-model-platform
Description: How AI/model features should be configured, called, tuned, gated and cost-tracked in any app. Covers the feature_key contract (code defaults + a live tunable row + one telemetry stream + an optional billing path), keeping prompt/model/pricing as DATA not constants, the single wrapper every model call goes through, the connect-then-activate lifecycle with a visible "needs attention" queue, the two billing modes (billed per use vs platform-absorbed), the spend gate and 402 out-of-credit flow, usage rows and the billing job that debits a ledger, attribution for crons, kill switches, error classes, model slots with fallback legs, abuse caps for free features, provisioning provider keys by API, and the anti-patterns that silently lose money or telemetry. This is a pattern to BUILD per repository. Read it BEFORE building any feature that calls a model API, before adding a feature key, before wiring a prompt or a model choice, before designing the settings page that tunes them, and before touching AI billing. Use when the user mentions AI features, model calls, OpenAI, Anthropic, Claude, GPT, prompts, feature keys, token cost, model settings, AI usage tracking, AI credits, insufficient funds, a 402, spend limits, "which model", "what did AI cost us", or connecting/validating a provider key. For the agent architecture built on top of this, read `internal-ai-agent-architecture`.
License: unknown
Instructions: 551 lines in SKILL.md · view on GitHub

Agent Skills spec issues

description: longer than 1024 characters
body: 551 lines (spec recommends under 500)

Files (1)

SKILL.md

The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub

Signals

Stars: 0
Forks: 0
Open issues: 0
Last commit (this folder): Oct 13, 2026 (16 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License: License unknown
Repository: github.com/Automate-Anything/claude-toolkit
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: GitHub github-graphql

More from Automate-Anything

Cite this page

ai-model-platform skill. Agent Mart. https://agentmart.dev/skills/automate-anything-ai-model-platform (last updated 2026-10-24)