My Claude Code toolkit: skills, commands, agents, hooks, and reusable workflow configs. Grab what you need.
antoniocascais/claude-code-toolkit
Agent Claude Code
Deep specialist seat pinned to Sonnet 5 (full model ID, bypasses the haiku alias remap) for the harder reasoning / verification role. Role and charge are supplied in the spawn prompt — a hard council seat, a recon verifier that cross-checks scout findings, or any task needing stronger reasoning. Full tool access to…
antoniocascais/claude-code-toolkit
Agent Claude Code
Fast specialist seat pinned to real Haiku 4.5 (full model ID, bypasses the haiku alias remap). Cheap parallel specialist whose role and charge are supplied in the spawn prompt — a council seat, a codebase recon scout, or any other low-cost specialist task. Full tool access to ground work in the actual repo.
antoniocascais/claude-code-toolkit
Agent Claude Code
Implements a fully-specified coding task from a written spec. Executes; does not design. Only use when explicitly dispatched with a spec file — do NOT auto-delegate for design, brainstorming, or open-ended work.
antoniocascais/claude-code-toolkit
Agent Claude Code
Claude Fable 5 agent, pre-tuned per Anthropic's Fable 5 prompting guide. Use for the hardest, longest-horizon, most ambiguous work — multi-hour/multi-day implementations, deep debugging, whole-repo review, dense-image/vision analysis, or anything where first-shot correctness on a complex spec matters. Not for routine…
antoniocascais/claude-code-toolkit
Agent Claude Code
Enhance knowledge base entries following Obsidian standards by implementing approved improvement plans from knowledge base reviews.
antoniocascais/claude-code-toolkit
Agent Claude Code
Architecture design and review specialist. Discusses system-design questions in an architecture context, and on request scores existing architecture against a rubric (Scalability, Coupling/Cohesion, Reliability, Security, Cost, Operability — 1-5 each), flags concrete issues, and recommends a direction with explicit…
antoniocascais/claude-code-toolkit
Agent Claude Code
Optimize task notes for Claude's session performance by cleaning outdated context and maintaining accurate project status.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: