/reprompter-goal-workflow

name: reprompter-goal-workflow
description: |
  RePrompter Improve output formats — compress a finished spec-XML prompt to a `/goal <objective>` command (Codex CLI, Claude Code v2.1.139+, Hermes), compile it to a runnable `.workflow.js` for Claude's dynamic Workflow tool, or deliver it to another model via headless-relay.
  Use when: "before /goal", "for /goal", "Codex /goal", "Claude Code /goal", "Hermes /goal", improve a goal prompt, "compile to workflow", "workflow preflight", "dynamic workflow"; or the headless-relay delivery step after a finished Single/Reverse prompt.
  Don't use for outcome-prose / One-Shot build briefs (delivered as-is), simple Q&A, or execution-only tasks.
  Outputs: /goal command card (Codex/Claude Code/Hermes); Workflow Command Card + runnable .workflow.js (Workflow preflight lane / Option H); optional relay delivery offer.
  Target score: spec >= 7/10.

RePrompter — `/goal`, Workflow script, and headless-relay delivery

> Mode skill of the `reprompter` plugin. Entry/routing: `../reprompter/SKILL.md`. Generate the spec prompt with `../reprompter-improve/SKILL.md`, then apply the format below. Content below is verbatim from root SKILL.md lines 58-211 (`/goal`), 212-356 (Workflow script) and 1481-1558 (headless-relay). `references/workflow-template.md` and `references/runtime/claude-workflow-runtime.md` are copied alongside; Repromptverse Option H is in `../reprompter-team/references/runtime-options.md`. `scripts/<name>` paths resolve to the bundled `../reprompter/scripts/<name>` (e.g. `node ../reprompter/scripts/workflow-command.js --help`). > > **Required reading:** `../reprompter/references/advanced-features.md`. The always-on rules in `../reprompter/SKILL.md` → "Core shared rules" (context check, uncertainty permission, WHAT not HOW) apply before any `/goal` compression or workflow compile.

Format: `/goal` command (Improve output)

When the user mentions `/goal`, `before /goal`, `for /goal`, "Codex /goal", "Claude Code /goal", "Hermes /goal", or asks to improve a goal prompt, run RePrompter before the goal is submitted.

This lane works on **Codex CLI** (any version exposing the `goals` feature), **Claude Code CLI v2.1.139+** (the release that shipped a native `/goal` slash command on 2026-05-11), and **Hermes Agent** (persistent goals documented in the v0.13.0 / 2026.5.7 release). These runtimes accept the same `/goal <objective>` shape, so the compression flow is identical; only the setup check and a few runtime-specific operational notes differ. If the target runtime is Claude surfaces without `/goal` support, OpenClaw, Grok CLI, Gemini, or another LLM, use Improve (spec-XML) or Repromptverse instead; do not emit a `/goal` command for runtimes that have no `/goal` surface.

Detecting the target runtime

Pick the runtime once, at the start of the lane, and pass it through to the Card:

| User signal | Runtime | |-------------|---------| | "Codex /goal", "for Codex /goal", explicit `codex` mention | **Codex CLI** | | "Claude Code /goal", "/goal in Claude Code", explicit `claude` / `claude-code` mention | **Claude Code CLI (≥ v2.1.139)** | | "Hermes /goal", "/goal in Hermes", explicit `hermes` / `hermes-agent` mention | **Hermes Agent** | | Bare "/goal" or "before /goal" with no runtime marker | **ASK** which runtime, with the three options as buttons; default to the user's primary CLI if known from session context |

Process:

1. Treat the input as **Single prompt mode** unless it clearly needs Repromptverse. 2. Detect the target runtime (table above). Carry the runtime label through the rest of the lane. 3. Render the **Goal Command Card** first, with `Runtime` populated from step 2. 4. Infer the user's real intent from the rough prompt: desired outcome, hidden constraint, success signal, and likely risk. 5. Build the rich expanded prompt first, using the normal RePrompter structure: goal/task, context, assumptions, requirements, constraints, execution notes, and success criteria. 6. Compress that expanded prompt into a dense one-line goal summary. This should feel like a summary of a long XML prompt, not a slightly polished copy of the user's rough sentence. The compression rule is identical across runtimes — both Codex's alpha `/goal` and Claude Code's v2.1.139+ `/goal` consume `<objective>` as a single argument. 7. Generate an exact copy-paste command: `/goal <summary of expanded prompt>`. 8. Do not put the full XML or Markdown document after `/goal`; only the compressed summary belongs in the command. 9. Include the expanded prompt basis after the command so the user can inspect what was compressed or send it as a follow-up normal message after the goal is set. 10. Tell the user to run the exact `/goal <summary of expanded prompt>` command in the runtime chosen at step 2. 11. Do not claim RePrompter can automatically intercept `/goal`; slash commands are user-invoked in both Codex and Claude Code unless the local runtime adds a separate hook.

Goal Command Card

Both runtimes shape the slash command as `/goal <objective>`. Render this card before the generated command:

| Field | Content | |-------|---------| | Goal Command | Exact one-line `/goal <summary of expanded prompt>` command | | Compressed From | `Expanded RePrompter prompt` | | Objective | One sentence naming the reprompted intent the runtime should pursue | | Runtime | `Codex CLI`, `Claude Code CLI (≥ v2.1.139)`, or `Hermes Agent` — whichever was detected in step 2 above | | Mode | `/goal preflight` | | Paste Into | Codex TUI prompt, Claude Code TUI prompt, or Hermes TUI prompt, as-is | | Risk Level | `low` / `medium` / `high`, based on blast radius | | Missing Inputs | Up to 3 unresolved unknowns; use documented assumptions for reasonable defaults and write `none` when the prompt is ready | | Verification | 2-4 checks the agent should run while pursuing the goal | | Quality | Before score → after score, with the weakest remaining dimension |

Then output:

/go