Install and onboard a user into LifeOS — the Life Operating System (current state → ideal state via TELOS + the Algorithm). The agentic installer detects your OS + harness, wires hooks with permission, scaffolds your USER tree, pulls in sources you provide, and runs the TELOS / current→ideal interview that seeds your…
Academic researcher using Claude's WebSearch. Called BY Research skill workflows only. Excels at multi-query decomposition, parallel search execution, and synthesizing scholarly sources.
Remy - Eccentric, curiosity-driven technical archaeologist who treats research like treasure hunting. Powered by OpenAI's flagship model via codex exec in deep-reasoning mode (reasoningeffort=high) with live web search; the model ID resolves from CROSSVENDOR in models.ts. Follows interesting tangents and uncovers…
Agent "Forge" from jSydorowicz21/Universal-AI-Infrustructure, covering forge — the uncompromising craftsman, identity, character, thinking skills — the point of me and evidence rules — non-negotiable.
Google cross-vendor agent running the top Gemini reasoning model via LIFEOS/TOOLS/GeminiSearch.ts --pro — a third vendor's opinion on public material, vendor panels and bake-offs, and grounded takes where Google Search grounding helps. PUBLIC data class only (same Tier-2 egress ceiling as GeminiResearcher). Never…
Multi-perspective researcher using Google Gemini with Search grounding, via LIFEOS/TOOLS/GeminiSearch.ts (NOT the gemini CLI, which cannot authenticate non-interactively here). Called BY Research skill workflows only. Breaks complex queries into 3-10 variations, launches parallel investigations for comprehensive…
Agent "Grok" from jSydorowicz21/Universal-AI-Infrustructure, covering jax — the public-lane runner, identity, when i'm invoked, how i work and self-verification (before returning).
Agent "Max" from jSydorowicz21/Universal-AI-Infrustructure, covering max — the last set of eyes, identity, character, thinking skills — the point of me and evidence rules — non-negotiable.
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.
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. Shortcut for the Cortex skill's recall workflow.
Relentless checkpointed discovery interview that interrogates a half-formed idea until its shape is clear, then hands off to ISA Scaffold. Routes to the ISA skill's Grill workflow. USE WHEN /grill-me, grill me, discovery interview, figure out the shape, brainstorm before scaffolding an ISA. NOT FOR filling an existing…
Check whether a site is down for everyone or just you — local probe + downforeveryoneorjustme API, with --deep for a 7-node worldwide sweep via check-host.net.
LifeOS upgrade — extract system improvements from content, monitor external sources, and scan bookmarks for upgrade opportunities. Shortcut for the Upgrade skill.
Interactive voice-narrated tutorial on the current conversation topic (or a named one) — ASCII diagrams, spoken lesson content, one question per beat, quizzes. Routes to the Teach skill's Teach workflow. USE WHEN /teach-me, teach me, tutorial, quiz me, learn mode. NOT FOR plain written explanations with no dialogue…
Interactive voice-narrated tutorial on the current conversation topic (or a named one). Shortcut for the Teach skill's Teach workflow. USE WHEN /tm, teach me, tutorial, quiz me.
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 jSydorowicz21/Universal-AI-Infrustructure.
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 jSydorowicz21/Universal-AI-Infrustructure.
Runs when you submit a prompt, before the agent sees it, executing PromptProcessing.hook.ts, SatisfactionCapture.hook.ts, ReminderRouter.hook.ts, VersionDrift.hook.ts, MemoryTurnStart.hook.ts, DriftReminder.hook.ts, AlgorithmNudge.hook.ts, TimeContext.hook.ts and ModelRungGuard.hook.ts (9 commands). From…
Runs when a tool call fails, executing EventLogger.hook.ts, AlgorithmNudge.hook.ts and LoopDetector.hook.ts (3 commands). From jSydorowicz21/Universal-AI-Infrustructure.