AI INFO FORGE
Claude agents and skills that don't rot.
Glowing circuit-board anvil being struck — the AI Info Forge mark
Hardened. Verified. Current.

A marketplace for tested, version-tracked Claude agents, skills, and prompts — plus the news, guides, and reviews to keep them working as the models keep moving.

Founder-rate sellers get a 10% platform fee for life (vs 14% standard) — first 100 sellers only.

Verified against current Claude versions

Every skill carries a freshness badge — green if it's been tested against the latest model, red if it's drifted. No more buying prompts that broke three releases ago.

A real marketplace, not a directory

Buy and sell Claude skills, agents, and prompts. Security-scanned uploads, fair revenue share, automated delivery.

Plus the guides you actually need

Reviews, recipes, and how-tos for getting real value from Claude in your workflow — written by people who use the skills they're recommending.

What's new — and what it breaks

Plain-English coverage of every Claude release, new feature, and ecosystem shift. The only question we answer: does this change what you should buy, sell, or stop using?

Scott Sokolowski, founder of AI Info Forge

Hi — I'm Scott. I'm running AI Info Forge because the Claude skills market is full of prompts that worked last month and break this month. Verified, drift-tested skills is the version of this market I wish existed. If you've felt the same friction, take a look around the shop, or join the list for updates when new prompts and tools ship.

— Scott Sokolowski, Founder

Current Claude Models

Listed newest to oldest. Pricing is per 1 million tokens (input / output). Buyers can match a product's pricing badge to the model below.

Claude Fable 5 claude-fable-5

A new tier above Opus. Anthropic's most powerful, most intelligent model. Use for the hardest research, long-horizon agentic work, and the deepest analysis. Same adaptive-thinking surface as Opus 4.7/4.8.

Context: 1M tokens Input: $10.00 / 1M Output: $50.00 / 1M
Claude Opus 4.8 claude-opus-4-8

The most capable Opus-tier model. Highly autonomous, state-of-the-art on long-horizon agentic work, knowledge work, and memory. Clearer, warmer writing than 4.7. 1M context window at standard pricing — no long-context premium.

Context: 1M tokens Input: $5.00 / 1M Output: $25.00 / 1M
Claude Opus 4.7 claude-opus-4-7

Previous-generation Opus. Strong on long-horizon agentic work, knowledge work, and vision tasks. Adaptive thinking only (no fixed budget tokens). 1M context window.

Context: 1M tokens Input: $5.00 / 1M Output: $25.00 / 1M
Claude Opus 4.6 claude-opus-4-6

Older Opus. Supports adaptive thinking (recommended) and up to 128K output tokens with streaming. Same 1M context window as newer Opus models.

Context: 1M tokens Input: $5.00 / 1M Output: $25.00 / 1M
Claude Sonnet 4.6 claude-sonnet-4-6

The best balance of speed and intelligence for high-volume production work. Supports adaptive thinking. 1M context, 64K max output tokens. About 60% cheaper than Opus for most workloads.

Context: 1M tokens Input: $3.00 / 1M Output: $15.00 / 1M
Claude Haiku 4.5 claude-haiku-4-5

Fastest and most cost-effective model in the family. Use for simple tasks, classification, lightweight extraction, or anything where latency matters more than depth. Smaller 200K context window.

Context: 200K tokens Input: $1.00 / 1M Output: $5.00 / 1M

Pricing reflects published Anthropic rates as of June 2026. Verified products on AI Info Forge are tested against Sonnet 4.6, Opus 4.8, and Haiku 4.5 so buyers see how each prompt holds up across price tiers. Fable 5 is tracked for drift on new listings — verification against Fable 5 will roll out once its rate limits stabilize.