Skip to content
Automation
Skill

/planner-clarify

Internal Auto-Harness planning skill for clarification intake. Use only inside the Planner subagent when it is producing .harness/intake.md and .harness/status.md.

From plugin
auto-harness
1520 skills26 agents8 commands5 hooks
+1

Claude Code

$ npx -y skills add redker56/auto-harness --skill planner-clarify --agent claude-code

SKILL.md

planner-clarify.SKILL.md
name: planner-clarify
description: Internal Auto-Harness planning skill for clarification intake. Use only inside the Planner subagent when it is producing .harness/intake.md and .harness/status.md.
user-invocable: false

Planner Clarify

This skill governs **Clarification Mode** for Auto-Harness.

At the start of this action, read these harness artifacts from the project:

  • `.harness/intake.md` when it already exists.
  • `.harness/status.md` when it already exists.

Then inspect the current project implementation only when the brief points to an existing project, codebase, or migration surface:

  • Read the current app structure, entrypoints, routes, components, services, tests, and config that define the existing constraints or compatibility surface.
  • Use the codebase to understand current reality and constraints; do not infer sprint scope, named defects, or implementation commitments from it.

Then read these skill references:

  • `references/protocols/file-ownership.md`
  • `references/clarification/core.md`
  • `references/clarification/product.md`
  • `references/clarification/architecture.md`
  • `references/clarification/stack.md`
  • `references/clarification/constraints.md`
  • `references/catalogs/architecture-options.md`
  • `references/catalogs/consistency-patterns.md`
  • `references/catalogs/frontend-patterns.md`
  • `references/catalogs/stack-options.md`
  • `references/templates/intake-template.md`

Follow these rules:

  • Write only `.harness/intake.md` and `.harness/status.md`.
  • Produce a relay-ready numbered clarification questionnaire for the Orchestrator.
  • Do not draft `.harness/spec.md` or `.harness/design-direction.md`.
  • If the user has not explicitly answered a clarification item, keep it unresolved rather than inferring it from the brief.
Read more
@redker56
Ships withauto-harness

Auto-Harness is a Claude Code plugin for longer software tasks that need planning, implementation, QA, fixes, retests, and a final report. Give it a product brief.

1520 skills26 agents1 MCP
Get the whole plugin

Stars on GitHub

Momentum

stars in total
15
Star history of redker56/auto-harness on GitHub, a chart by star-history.com

Other skills on auto-harness.

evaluator-write-qa

evaluator-write-qa

Internal Auto-Harness evaluator skill for sprint QA and QA report writing. Use only inside the Evaluator subagent during qa mode.

More skills from other plugins.

agent-builder

agent-builder

Load immediately after an Agent intent, before the first agent_builder_* call. Governs how you create, configure, test, and…

n8n2w209k
@n8n-io@n8n-ioInstall Skill
browser-use

browser-use

Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers…

@browser-use@browser-useInstall Skill
add-anydoc

add-anydoc

Add local office-document-to-Markdown conversion to NanoClaw agent containers with the pinned Firecrawl AnyDoc CLI. Use when…

@nanocoai@nanocoaiInstall Skill

Questions about planner-clarify.

Which coding agents can use planner-clarify?
planner-clarify installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.