lev-os/agents

propose

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.

原文语言：英语

auto-enrich

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

原文语言：英语

cdo

Routes adaptive multi-agent deliberation with fractal context cycles. Use when using /cdo, think/deep/debug/parliament work, planning multi-wave runs with skills per node and a judge, or long runs paired with autoresearch scheduling.

原文语言：英语

explain

Use when the user needs a catch-up, concept explanation, goal closeout, current-state refresh, Lev context mapping, or a visual guided lesson.

原文语言：英语

lev-relay

List, find and read Claude Code, native OMO/Senpi and OMP sessions from permitted user-owned JSONL, bind this Codex relay to one session, show summaries or sanitized verbatim trace, and manage requested same-chat monitoring. Use when JP asks Lev Relay for…

原文语言：英语

dotfiles-sync

Reconcile chezmoi dotfiles and the separate ~/.agents Git repository using commits and merges, with semantic conflict review and quiet scheduled sync.

原文语言：英语

arch

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

原文语言：英语

impeccable

Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells,…

原文语言：英语

release

Use when preparing a project release, updating release documentation with --docs, or reconciling implemented changes with project work records.

原文语言：英语

skill-builder

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

原文语言：英语

ux

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.

原文语言：英语

ai-slop-cleaner

Run an anti-slop cleanup/refactor/deslop workflow

原文语言：英语

eval-builder

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

原文语言：英语

now

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.

原文语言：英语

prior-art

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

原文语言：英语

writing

Use when drafting or revising human-facing prose, titles, articles, posts, marketing copy, READMEs, or docs; also when asked to humanize text, remove AI writing patterns, or match a writer's voice. Keep code cleanup in its own lane.

原文语言：英语

codebase-memory

Use the codebase knowledge graph for structural code queries. Triggers on: explore the codebase, understand the architecture, what functions exist, show me the structure, who calls this function, what does X call, trace the call chain, find callers of, show…

原文语言：英语

coder

Run and supervise Lev-aware coding workers across Codex, Claude Code, Gemini, OpenCode, Pi, OmO Native (omo), or oh-my-pi (omp), including CAAM identity handling and single-worker or coder-reviewer SDD modes.

原文语言：英语

humanizer

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…

原文语言：英语

exec

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

原文语言：英语

goal-exec

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

原文语言：英语

interview

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

原文语言：英语

lev-plan

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…

原文语言：英语

lev

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

原文语言：英语

orch

Use when coordinating a multi-step goal across agents, skills, Lev lifecycle routes, scheduling, research, implementation, review, or human decisions.

原文语言：英语

research

Use when current external facts, source-backed comparisons, investigations, or recent community evidence are needed.

原文语言：英语

tools

Use when a task needs GitHub gh, Notion ntn, Slack CLI/API, explicit Exa transport, AgentMail, optional Herdr pane transport, or terminal-agent coordination through one self-contained integration router.

原文语言：英语

work

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

原文语言：英语

ws

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

原文语言：英语

mail

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

原文语言：英语

scroll-world

Build an immersive scroll-scrubbed "fly through the world" landing page for any industry or brand using Higgsfield. As the visitor scrolls, a pre-rendered camera flies from outside each scene into its interior, then flows on to the next scene with NO cuts —…

原文语言：英语

agent-field-kit

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.

原文语言：英语

cass-coverage

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…

原文语言：英语

stack

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

原文语言：英语

visual-explainer

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.

原文语言：英语

tribunal

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.

原文语言：英语

close

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

原文语言：英语

archify

Create polished, validated architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as explorable standalone HTML with inline SVG, dark/light themes, optional trace motion, and PNG/JPEG/WebP/SVG/WebM export. Accept plain-language requirements…

原文语言：英语

capture

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.

原文语言：英语

domain-modeling

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

原文语言：英语