/reprompter-team

name: reprompter-team
description: |
  RePrompter team execution (Repromptverse / Agent Teams) — score the raw task, plan a 2-5 agent team, write a reprompted prompt per agent, run it on the detected runtime (Grok CLI, Hermes, Claude Code TeamCreate/Workflow/tmux, OpenClaw, Codex, or sequential), then evaluate and retry.
  Use when: "repromptverse", "reprompter teams", "smart run", "smart agents", "run with quality", "engineering/ops/research/marketing swarm", multi-agent tasks, audits, "parallel", tasks spanning 2+ systems; or a Build (One-Shot) brief the user wants "split across a team".
  Don't use for single-prompt improvement (use reprompter-improve), simple Q&A, or casual chat.
  Outputs: optional team brief + per-agent prompts + Agent Cards (Plan/Status/Result) + reprompt quality scorecard + final synthesis.
  Target score: per-agent >= 8/10.

RePrompter — Team execution (Repromptverse)

> Mode skill of the `reprompter` plugin. Entry/routing: `../reprompter/SKILL.md`. Content below is verbatim from root SKILL.md lines 594-840 and 957-993. Phase 3 runtime detail (root lines 841-956 and 994-1283: runtime auto-pick, tool-schema guard, Options A-H) is in `references/runtime-options.md`; Settings (root 1832-1922) is in `references/settings.md`; Hermes Agent and Grok CLI support (root 2000-2071) is in `references/hermes-grok-support.md`. Templates (`repromptverse`, `swarm`, `team-brief`, `*-swarm`), `outcome-schema.md` and `references/runtime/*.md` are copied alongside. `scripts/<name>` paths resolve to the bundled `../reprompter/scripts/<name>` (e.g. `node ../reprompter/scripts/run-supervisor.js`). > > **Required reading:** `../reprompter/references/advanced-features.md` (capability routing, layered context, artifact gate, flags, telemetry, Flywheel). The always-on rules in `../reprompter/SKILL.md` → "Core shared rules" (context check, uncertainty permission, WHAT not HOW) apply to every per-agent prompt.

Team execution: Repromptverse (Agent Teams)

TL;DR

Raw task in → quality output out. Every agent gets a reprompted prompt.

Phase 1: Score raw prompt, dimension interview if needed, plan team, show Agent Cards (YOU do this, ~45s)
Phase 2: Write XML-structured prompt per agent (YOU do this, ~2min)
Phase 3: Launch agents (tmux, TeamCreate, Workflow tool, sessions_spawn, Codex, or sequential) (AUTOMATED)
Phase 4: Show Result Cards, score, retry if needed (YOU do this)

**Key insight:** The reprompt phase costs ZERO extra tokens — YOU write the prompts, not another AI.

Repromptverse control plane (Microsoft-inspired)

Every multi-agent run must include:

1. **Routing policy** — who speaks next and why (selector-style routing for non-trivial teams) 2. **Termination policy** — max turns, max wall time, and no-progress stop condition 3. **Artifact contract** — one writer per output file, fixed schema for handoffs 4. **Evaluator loop** — score each artifact, retry only with delta prompts (max 2 retries)

Use `references/repromptverse-template.md` to enforce this contract.

Domain profile auto-load rules (lazy-load, on demand):

• Marketing intent (`campaign`, `launch`, `growth`, `seo`, `content calendar`, `funnel`) -> `references/marketing-swarm-template.md`
• Engineering intent (`architecture`, `feature delivery`, `refactor`, `migration`, `test coverage`) -> `references/engineering-swarm-template.md`
• Ops intent (`incident`, `uptime`, `gateway`, `latency`, `cron`, `slo`, `health`) -> `references/ops-swarm-template.md`
• Research intent (`benchmark`, `compare`, `tradeoff`, `analysis`, `research`) -> `references/research-swarm-template.md`

Then merge with `references/repromptverse-template.md` for routing/termination/evaluation contract and add task-specific constraints.

Canonical implementation for deterministic routing lives in `scripts/intent-router.js`. If docs and code ever diverge, the script is the source of truth for benchmark/testing paths.

Phase 1: Team plan (~45 seconds)

1. **Score raw prompt** (1-10): Clarity, Specificity, Structure, Constraints, Decomposition

• Phase 1 uses 5 quick-assessment dimensions. The full 6-dimension scoring (adding Verifiability) is used in Phase 4 evaluation.

2. **Dimension Interview gate** — check which askable dimensions scored < 5 (see Dimension Interview section below). In autonomous or batch-destined runs, prefer documented assumptions over blocking questions when a reasonable default exists. 3. **Pick mode:** parallel (independent agents) or sequential (pipeline with dependencies) 4. **Define team:** 2-5 agents max, each owns ONE domain, no overlap (informed by interviewContext if interview ran) 5. **Show Plan Cards** (see Agent Cards section below) 6. **User confirmation gate** — "Team plan ready. Proceed to execution?" User can approve, adjust, or cancel. In automated/batch runs, auto-proceed. 7. **Write team brief** to `/tmp/rpt-brief-{taskname}.md` (use unique tasknames to avoid collisions; includes interviewContext section if interview ran)

Dimension Interview (Repromptverse only)

Score-driven interview for Repromptverse mode. Distinct from Single mode's "Smart Interview" (which uses a standard question list). The Dimension Interview derives questions from low-scoring raw prompt dimensions.

Trigger logic

scores = score_raw_prompt(rawInput)  # 5 dimensions from step 1

# Structure is EXCLUDED — reprompter fixes structure via templates.
# Only 4 dimensions are interview-eligible:
askable = [d for d in scores if d.name != "Structure" and d.value <= 5]

# Threshold: less-than-or-equal. Scores of 5 ARE borderline and trigger questions.
if len(askable) == 0:
    SKIP interview → proceed to step 3 (pick mode)
elif len(askable) <= 2:
    ASK 1-2 questions (one per low dimension)
else:
    ASK 3-4 questions (max 4, prioritized by lowest score first)

Dimension-to-question mapping

| Dimension | Score < 5 triggers | Question approach | |-----------|-------------------|----------------