Agents

Typed tick loops with FlowMind validation and parallel tick dispatch. Use when running /ll, recurring pipelines, quality loops, or autonomous scheduler ticks.

Routes UX/product design runs, user research/persona synthesis, wireframes, flows, IA, pencil visuals, and agentic CLI UX. Infers full run vs research vs CDO-backed persona mode from context, asking one question only when ambiguous.

Use when attaching a session to a workstream, or scanning, finding, resuming, merging, branching, or untangling Lev workstreams.

Routes adaptive multi-agent deliberation with fractal context cycles. Use when using /cdo, think/deep/debug/parliament work, or long runs paired with autoresearch scheduling.

Use when routing intent into Lev lifecycle work, clarifying an uncertain next step, or invoking and diagnosing the Lev CLI and runtime.

Compose evidence-backed sales pages, lessons, technical explainers, feedback surfaces, dashboards, and document collections as one deterministic RenderSpec component graph, then render, QA, publish, or attach the HTML.

Use when the user asks to prove, spike, prototype, POC, validate a production path, compare landing zones, or decide whether an idea should move to propose, monitor, reject, or archive.

Single-model forced-framing diversity with inline synthesis. Turn-manager protocol: unfold → synthesize → reduce → conclude. Use for decision synthesis and strategic alignment. Cheaper than /cdo, richer than /think.

Architecture reasoning with trade-offs, ADRs, C4, and fitness functions. Use when user asks for system design, tech selection, architecture review, or ADR drafts.

cass CLI session search across coding agents with JSON or robot output. Use when user needs session evidence, cross-agent search, handoff recovery, or transcript-backed claims.

Use when a long brainstorm or brain dump needs deep capture, prior-art routing, and durable next states.

Use when running execution-ready task slices, dispatching verified `lev exec` flows, or reviewing implementation work in the Exec lane.

Agent mail for multi-session coordination. Wraps levmail CLI. Register, send, inbox, claim, broadcast, roster.

Checkpoint sync for the current checkout and recursive dirty submodules. In feature branches, paired main checkout and feature->main landing require explicit --main.

Use when routing tracked work through lifecycle lanes, resolving workstream context, or deciding which lifecycle skill owns the next entity transition.

Use when verified work is ready for QA, acceptance, checkpointing, learning, recommendation, and handoff.

Run and supervise Lev-aware coding workers across Codex, LazyCodex, Claude Code, Gemini, OpenCode, or Pi, including CAAM identity handling and single-worker or coder-reviewer SDD modes.

Use when listing, inspecting, running, or managing prompt-stack sessions. Triggers on "stack", "list stacks", "show stack", "init stack", "run stack", "stack status".

Config-driven workshop intake for URLs, repos, media, PDFs, and skill packages. Use when user wants intake, download, or external content analyzed with project playbooks, ending with a brief, routed recommendation, validation plan, and action dashboard.

Read-only dashboard projecting lifecycle triggers into entities and next actions. Use mid-flow via /sitrep or /status.

Use when inventorying conversation state into durable artifacts with an operator-visible source-fidelity table, routing faithful items toward interview, planning, proposal, or execution, or deep-processing a brain dump.

Use when closing or pausing a session by updating workstream state and copying a resume prompt.

Use when compiling aligned simple intent or a source-faithful Lev plan into a reviewable slice map or one execution-ready Lev task. It does not create or repair broad plans.

[OMX] Adversarial dynamic e2e QA workflow - generate hostile scenarios, test, verify, fix, report, and clean up

Use macOS Terminal.app Full Disk Access as a proxy to copy TCC-protected files such as Messages/chat.db or AddressBook into a readable location for agent workflows.

Publishes static folders or files to instant shareable here.now URLs. Use when the user wants publish, host, deploy, share a link, or put HTML or assets on the web.

Compile captured or designed intent into a source-faithful Lev plan, deepen or review an existing plan, and manage its lifecycle under `.lev/pm/plans/`. Use for human runbooks, migrations, architecture plans, multi-slice roadmaps, plan review, or plan state transitions; route SDLC packets to propose and non-coding work to its domain executor.

Use when any research, search, or information gathering is needed.

Run one neutral prompt independently across every discovered model from selected CLI providers, then compare all answers and failures. Use for naming, short judgment questions, sanity checks, and cross-model test matrices; never use it to execute coding work.

Scaffolds, lists, and runs workflow skills under flows directories. Use when creating workflows, listing /workflow options, or executing a workflow skill by name.

Structured agent-to-human pings for approvals, selections, and open questions across surfaces. Use for human-in-the-loop or async feedback.

Convert an explicit user request into a Codex goal and pass its chosen coder, Lev, LazyCodex, SDD, or Fable execution flags to $coder.

Rewrite AI-sounding text so it reads naturally without changing what it says. Use when editing or reviewing prose for inflated claims, sales language, vague sources, repetitive structure, stock AI words, passive voice, filler, or chatbot artifacts. Based on Wikipedia's "Signs of AI writing."

Use when guiding decision interviews that produce a design artifact in .lev/pm/designs before proposal or implementation planning.

Thin Notion API CLI for doctor, search, queries, pages, and comments. Use when changing notionctl/lev-notionctl or keeping triage and policy out of the CLI surface.

Use when you need an evidence-first provenance report from `cass`, repo docs, `.lev`, `~/.agents/diagrams`, `qmd`, or Grep/Glob tools.

Routes any job into the right lev workflow by complexity and returns runnable next steps. Use when you want one-shot autonomous SDLC from quick fix through epic.

Plan a huge chunk of work — more than one agent session can hold — as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.

Use when source-faithful planning artifacts need simple host-only, standard, or deep enrichment before SDLC proposal review or a non-coding domain handoff.

Use when designing or improving Lev eval packs, inline FlowMind evaluation policy, owner-local runtime scenarios, assurance sizing, adversarial field probes, or promotion gates.

Build with rp-cli context builder plan → implement

Runs agent-browser to open pages, snapshot refs, click, fill, screenshot, and extract. Use when web tests, forms, or interactive scraping need a real browser.

Build a 3-week coding-agent capture dashboard. Cross-references cass session inventory with .lev/pm/ workstream/handoff citations, detects resume-chain lineage, classifies orphan chains against the workstream registry, emits a canonical coverage.json + thin static viewer. Use when auditing how much agent work is captured by Lev workstreams, finding orphan transcripts, building a healing pipeline, or scheduling a weekly coverage report.

Use when reconciling chezmoi local-vs-remote drift, reviewing pending machine-state changes, or performing safe remote-first dotfiles sync across machines.

Code review workflow using rp-cli git tool and context_builder

Use when creating skills, converting docs/repos/PDFs to skills, installing external skills, auditing skill security, or merging skills

Portable coding-agent bootstrap bundle (CLI toolchain, PATH wiring, ops skills). Use when a local, remote, or container env is missing dcg, ntm, cass, ubs, defendr, or agentmail-cli.

Reference snapshot of the absorbed domain-modeling workflow; current work routes through skill://interview.

Authors FlowMind .flow.yaml graphs with validate, fix, promote, and measure steps. Use when user writes or audits flows, fixes violations, or advances lifecycle quality.

Refactoring assistant using rp-cli to analyze and improve code organization

Filesystem-first local skill lookup and ranking from lev-skills inventory. Use when work, lev, or hubs need to discover installed skills without low-quality fallbacks.

Specialist visual-authoring guide for diagrams, dense comparisons, plans, and tables. Decomposes visual requirements into primitives that can render standalone or compose inside lev.now RenderSpec pages.

Runs long Codex improve-verify loops with metrics and logged artifacts. Use when you want unattended overnight fix, debug, security, or ship workflows, not one-shot help.

Deep investigation with rp-cli commands: tools gather evidence, follow-up reasoning synthesizes selected context

Export a ChatGPT-ready Question / Plan / Review prompt using rp-cli