Agent
Academic researcher using Claude's WebSearch. Called BY Research skill workflows only. Excels at multi-query decomposition, parallel search execution, and synthesizing scholarly sources.
Agent
Academic researcher using Claude's WebSearch. Called BY Research skill workflows only. Excels at multi-query decomposition, parallel search execution, and synthesizing scholarly sources.
Agent
Role: Academic researcher using Claude's WebSearch. Excels at multi-query decomposition, parallel search execution, and synthesizing scholarly sources.
Agent
Remy - Eccentric, curiosity-driven technical archaeologist who treats research like treasure hunting. Powered by OpenAI's latest GPT-5.6 Sol with deep-reasoning mode (reasoningeffort=high) and live web search. Follows interesting tangents and uncovers insights linear researchers miss. TypeScript-focused.
Agent
Role: Eccentric, curiosity-driven technical archaeologist. Treats research like treasure hunting. Powered by OpenAI's latest GPT-5.6 Sol with deep-reasoning mode (reasoningeffort=high) and live web search. TypeScript-focused.
Agent
OpenAI-family cross-vendor agent — runs GPT-5.6 Sol via codex exec. TWO MODES set by the spawn prompt. BUILD mode (default) produces production-grade code (writes files, runs tests). AUDIT mode (read-only) is the cross-vendor verification pass at E4/E5 VERIFY — surfaces Anthropic-family blind spots the Claude executor…
Agent
Role: OpenAI-family code producer. Runs GPT-5.6 Sol via codex exec at modelreasoningeffort=high (xhigh available, gated on {{PRINCIPALNAME}}'s call — see flag table). Specialization: code quality and completeness. Writes code; does not research (that's the Researchers' job).
Agent
Multi-perspective researcher using Google Gemini. Called BY Research skill workflows only. Breaks complex queries into 3-10 variations, launches parallel investigations for comprehensive coverage.
Agent
Role: Multi-perspective researcher using Google Gemini. Breaks complex queries into 3-10 variations, launches parallel investigations for comprehensive coverage.
Agent
Johannes - Contrarian, fact-based researcher using xAI Grok API. Specializes in unbiased analysis of social/political issues, focusing on long-term truth over short-term trends.
Agent
Role: Contrarian, fact-based researcher using xAI Grok API. Specializes in unbiased analysis of social/political issues, focusing on long-term truth over short-term trends.
Agent
Ava - Investigative analyst using Perplexity API for web research. Called BY Research skill workflows only. Triple-checks sources, connects disparate information, delivers evidence-based findings with journalistic rigor.
Agent
Role: Investigative analyst using Perplexity API for web research. Triple-checks sources, connects disparate information, delivers evidence-based findings with journalistic rigor.
Command
Search prior work to add context to a request, or browse previous sessions on a topic. Use before/after a request to ground it in past work, or standalone to recall and familiarize before asking.
Command
Search prior work to add context to a request, or browse previous sessions on a topic. Shortcut for ContextSearch skill.
Command
Extract system improvements from content, monitor external sources, and scan bookmarks for upgrade opportunities. Shortcut for Upgrade skill (formerly PAIUpgrade).
Hook
Runs before the agent uses a tool for Bash, Skill, Agent, AskUserQuestion, Bash, Write, Edit and MultiEdit tool calls, executing ContextReduction.hook.sh, AgentInvocation.hook.ts, TabState.hook.ts and PreToolGuard.hook.ts (4 commands). From DorShaer/Husk.
Hook
Runs after a tool call finishes for Agent, WebFetch, WebSearch, AskUserQuestion, Write, Edit and MultiEdit tool calls, executing AgentInvocation.hook.ts, Safety.hook.ts, TabState.hook.ts, ISASync.hook.ts, CheckpointPerISC.hook.ts and EventLogger.hook.ts (11 commands). From DorShaer/Husk.
Hook
Runs when a session ends, executing WorkCompletionLearning.hook.ts, SessionCleanup.hook.ts, UpdateCounts.hook.ts, MemoryHealthGate.hook.ts, DocIntegrity.hook.ts and IntegrityCheck.hook.ts (6 commands). From DorShaer/Husk.
Hook
Runs when you submit a prompt, before the agent sees it, executing PromptProcessing.hook.ts, SatisfactionCapture.hook.ts, ReminderRouter.hook.ts and MemoryTurnStart.hook.ts (4 commands). From DorShaer/Husk.
Hook
Runs when a tool call fails, executing EventLogger.hook.ts and AlgorithmNudge.hook.ts (2 commands). From DorShaer/Husk.
Hook
Runs on the TaskCreated event, executing TaskGovernance.hook.ts. From DorShaer/Husk.
Hook
Runs on the ConfigChange event, executing EventLogger.hook.ts. From DorShaer/Husk.
Hook
Runs when a session starts, executing HookHealer.hook.ts, KittyEnvPersist.hook.ts, LoadContext.hook.ts, FreshnessCache.ts and SettingsBackport.ts via bun with --quiet, --system, --user and --output (5 commands). From DorShaer/Husk.
Hook
Runs when the agent finishes a response, executing LastResponseCache.hook.ts, TabState.hook.ts, VoiceCompletion.hook.ts, ISARenderOnStop.hook.ts, StopGates.hook.ts and MemoryReviewFire.hook.ts (6 commands). From DorShaer/Husk.