Results for “rekall”

操作并扩展NanoClaw v2，这是ECC基于claude -p构建的零依赖会话感知REPL。

Redige recurso especial (CPC 1.029 + CF 105 III) e recurso extraordinario (CF 102 III), com prequestionamento obrigatorio, repercussao geral no RE (1.035), regime de repetitivos (1.036-1.041) e a regra NOVA de feriado local (Lei 14.939/2024 + STJ AREsp 2.638.376 — nao e mais intempestividade automatica). Use quando o operador disser REsp, recurso especial, RE, recurso extraordinario, repercussao geral, repetitivo, prequestionamento, levar pro STJ/STF.

Operate and extend NanoClaw v2, a zero-dependency session-aware REPL built on Claude's -p mode.

Operate and extend NanoClaw v2, ECC's zero-dependency session-aware REPL built on claude -p.

Use the status-briefing skill to run `pk-reconcile session-start`, then

Restore working context saved earlier by /context-save. Loads the most recent saved state (across all branches by default) so you can pick up where you left off — even across Conductor workspace handoffs. Use when asked to "resume", "restore context", "where was I", or "pick up where I left off". Pair with /context-save. Formerly /checkpoint resume — renamed because Claude Code treats /checkpoint as a native rewind alias in current environments. (gstack)

Operate and extend NanoClaw v2, ECC's zero-dependency session-aware REPL built on claude -p.

Operate and extend NanoClaw v2, a zero-dependency session-aware REPL built on claude -p, with commands for model switching, skill loading, session branching, search, compaction, export, and metrics.

Alias for $plan --consensus

Renewal-Health Analyst

Build or modify a RAG retrieval pipeline with vector store search, corpus routing, citation rendering, and book fidelity enforcement.

Runs a full retrospective and dev cycle analysis, chaining /recall and /new-features to reconstruct what went wrong, extract lessons learned, identify rework patterns, and synthesize feature ideas from the findings.

Restore working context saved earlier by /context-save. (gstack)

FREE — God-tier long-context memory for AI agents. Injects 500K-1M clean tokens, auto-summarizes with tone/intent preservation, compresses 14-turn history into 800 tokens.

Mines git history and codebase to reconstruct the development lifecycle, identify sequential and parallel patterns, and produce actionable recommendations for future iterations.

Resume a paused experiment. Checkout the experiment branch, read results history, continue iterating. Use when the user runs /ar:resume or asks to pick up a previously started autoresearch experiment.

Pauses mid-conversation to reassess direction, assumptions, and bias, then recommends whether to continue, pivot, or pause.

Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution

Refactors code by renaming variables, methods, classes, and types to improve clarity and intent, with automatic testing and commits after each rename.

FREE — God-tier long-context memory for AI agents. Injects 500K-1M clean tokens, auto-summarizes with tone/intent preservation, compresses 14-turn history into 800 tokens.

Use quando o usuário pede para executar Codex CLI (codex exec, codex resume) ou referencia OpenAI Codex para análise de código, refatoração ou edição automatizada. Usa GPT-5.2 por padrão para engenharia de software de ponta.

Start voice calls via the OpenClaw voice-call plugin.

Create and execute durable repo-native multi-goal plans over Codex goal mode artifacts.

Resume an interrupted AgenTeam run with verify-first strategy.

Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing. Uses GPT-5.2 by default for state-of-the-art software engineering.

FREE — God-tier long-context memory for AI agents. Injects 500K-1M clean tokens, auto-summarizes with tone/intent preservation, compresses 14-turn history into 800 tokens.