[go: up one dir, main page]

Claude Fast Code Kit 5.5 is here: Fable-optimized, with resumable nested sub-agents and dynamic workflows. Read the playbook.
Claude FastClaude Fast

Claude Code

Everything you need to master Claude Code, Web & Desktop
Tools, MCPs, Skills, Extensions & Advanced Techniques

What Claude Code /compact keeps and loses, straight from Anthropic's docs. The full survival table plus how to make rules and skills persist.

Guide
Mechanics

What Claude Code /compact keeps and loses, straight from Anthropic's docs. The full survival table plus how to make rules and skills persist.

2,000

GLM 5.2 vs Opus 4.8 vs Sonnet 5: the only clean benchmark comparisons, why cross-vendor numbers mislead, pricing, open weights, and which to use.

Models

GLM 5.2 vs Opus 4.8 vs Sonnet 5: the only clean benchmark comparisons, why cross-vendor numbers mislead, pricing, open weights, and which to use.

2,100

GLM 5.2 is Z.ai's open-weights MIT model: 753B MoE, 1M context, $1.40/$4.40 API. Benchmarks, self-host reality, and how it stacks up vs Claude.

Models

GLM 5.2 is Z.ai's open-weights MIT model: 753B MoE, 1M context, $1.40/$4.40 API. Benchmarks, self-host reality, and how it stacks up vs Claude.

2,000

Sonnet 5 vs Opus 4.8 compared: Opus leads coding and reasoning by 0.5 to 6.6 points; Sonnet 5 ties knowledge work at ~40% less cost.

Models

Sonnet 5 vs Opus 4.8 compared: Opus leads coding and reasoning by 0.5 to 6.6 points; Sonnet 5 ties knowledge work at ~40% less cost.

2,200

Claude Sonnet 5 scores 63.2% agentic coding at $2/$10 per million tokens (intro), closing the gap with Opus 4.8. Specs, benchmarks, pricing.

Models

Claude Sonnet 5 scores 63.2% agentic coding at $2/$10 per million tokens (intro), closing the gap with Opus 4.8. Specs, benchmarks, pricing.

2,400

OpenAI's GPT-5.6 family (Sol, Terra, Luna): pricing, benchmarks, the government-limited release, and how Sol compares to Claude Opus 4.8.

Models

OpenAI's GPT-5.6 family (Sol, Terra, Luna): pricing, benchmarks, the government-limited release, and how Sol compares to Claude Opus 4.8.

2,000

Claude Code Artifacts turn session work into live, shareable pages at a versioned URL. Private by default, in beta for Team and Enterprise.

Guide
Mechanics

Claude Code Artifacts turn session work into live, shareable pages at a versioned URL. Private by default, in beta for Team and Enterprise.

2,100

Claude Code sub-agents are now resumable via SendMessage and nest 5 levels deep. The persistent sub-agent pattern, field data, and the gotchas.

Guide
Agents

Claude Code sub-agents are now resumable via SendMessage and nest 5 levels deep. The persistent sub-agent pattern, field data, and the gotchas.

2,600

Claude Code subagents can now spawn their own subagents, capped at depth 5. How nesting works, the workflows it unlocks, and the token costs.

Guide
Agents

Claude Code subagents can now spawn their own subagents, capped at depth 5. How nesting works, the workflows it unlocks, and the token costs.

2,600

Is Claude Fable 5 free? It was, June 9-22, now usage credits at $10/$50 per million on the API. Pricing, the credits switch, and current access.

Guide
Development

Is Claude Fable 5 free? It was, June 9-22, now usage credits at $10/$50 per million on the API. Pricing, the credits switch, and current access.

2,100

Claude Fable 5 benchmarks: state of the art on coding, finance, physics, and vision. Specs, the Mythos 5 split, safety, and release details.

Models

Claude Fable 5 benchmarks: state of the art on coding, finance, physics, and vision. Specs, the Mythos 5 split, safety, and release details.

2,400

Claude Code Dynamic Workflows vs Agent Teams: a side-by-side comparison and a clear rule for when to use each. Where ultracode fits.

Guide
Development

Claude Code Dynamic Workflows vs Agent Teams: a side-by-side comparison and a clear rule for when to use each. Where ultracode fits.

0

Ultracode sends xhigh effort plus auto-triggered Dynamic Workflows. How it differs from xhigh, max, and ultrathink, plus the real token cost.

Guide
Development

Ultracode sends xhigh effort plus auto-triggered Dynamic Workflows. How it differs from xhigh, max, and ultrathink, plus the real token cost.

2,300

Why dynamic workflows exist, the three failure modes they fix, the six patterns, and how the harness runs. Beginner-friendly.

Guide
Development

Why dynamic workflows exist, the three failure modes they fix, the six patterns, and how the harness runs. Beginner-friendly.

0

Claude Opus 4.8 API pricing ($5/$25 per 1M tokens), benchmarks, specs, and whether it is free. Grounded in Anthropic's official release.

Models

Claude Opus 4.8 API pricing ($5/$25 per 1M tokens), benchmarks, specs, and whether it is free. Grounded in Anthropic's official release.

0

Managing Claude Code teams needs one owner: the agent manager. The role, a DRI checklist, and a 90-day playbook for Claude Code at scale.

Guide
Development

Managing Claude Code teams needs one owner: the agent manager. The role, a DRI checklist, and a 90-day playbook for Claude Code at scale.

2,000

How to run Claude Code in monorepos, legacy codebases, and enterprise repos. 8 strategies for navigating millions of lines at scale.

Guide
Development

How to run Claude Code in monorepos, legacy codebases, and enterprise repos. 8 strategies for navigating millions of lines at scale.

2,100

Skills can be scoped to file paths. Workflows load only where they apply. Here is how, plus the rules vs workflows mental model.

Guide
Mechanics

Skills can be scoped to file paths. Workflows load only where they apply. Here is how, plus the rules vs workflows mental model.

2,100

One CLAUDE.md does not scale. Layer them per subdirectory. Claude walks the tree, loads the right rules, and your context stays lean.

Guide
Mechanics

One CLAUDE.md does not scale. Layer them per subdirectory. Claude walks the tree, loads the right rules, and your context stays lean.

2,100

Claude Code is a model plus a harness. The AI layer of skills, hooks, agents, and MCPs matters more than the model. Here is how it works.

Guide
Mechanics

Claude Code is a model plus a harness. The AI layer of skills, hooks, agents, and MCPs matters more than the model. Here is how it works.

2,100

Your CLAUDE.md goes stale fast. A stop hook can spawn a headless Claude session to review changes and propose rule updates after each turn.

Tools
Hooks

Your CLAUDE.md goes stale fast. A stop hook can spawn a headless Claude session to review changes and propose rule updates after each turn.

2,000

Grep slows down on big codebases. LSP gives Claude Code symbol-level search through an MCP server. Build it or use ours. Token costs included.

Tools
Mcp Extensions

Grep slows down on big codebases. LSP gives Claude Code symbol-level search through an MCP server. Build it or use ours. Token costs included.

2,150

Plugins turn your personal Claude Code setup into a shareable bundle. Skills, hooks, MCPs in one install. Org rollout patterns inside.

Tools
Mcp Extensions

Plugins turn your personal Claude Code setup into a shareable bundle. Skills, hooks, MCPs in one install. Org rollout patterns inside.

2,100

Connect a Google Ads MCP to Claude Code. Manage PMax, Search, Shopping campaigns, audiences, and conversions from your terminal in 2026.

Tools
Mcp Extensions

Connect a Google Ads MCP to Claude Code. Manage PMax, Search, Shopping campaigns, audiences, and conversions from your terminal in 2026.

2,456
Claude Fast Shopify Kit
New

Shopify Kit just dropped

Your in-house Shopify x Claude team for Growth, CRO, Paid ads, retention, SEO, ops and Media gen.

Learn more
Master Claude AI Web, Desktop & Code!