hyperflow-scope

Hyperflow planning phase. Use when a task is clear enough to decompose into batched steps before writing code — verbs like scope, decompose, "plan out", "break down", "plan this". Read-only with respect to source; writes a task file to .hyperflow/tasks/<slug>.md, then hands off to hyperflow-dispatch.

hyperflow Plugin
ai agency Category

Allowed Tools

No tools specified

Provided by Plugin

hyperflow

Fifteen specialized slash commands turn one Claude session into a structured multi-agent engineering pipeline. Thinking models orchestrate, triage, and review; worker models execute in parallel — every step is a Worker → Reviewer pair, and every non-trivial phase fans into sub-phases with their own reviewers. Auto-routing is on by default — say 'audit the diff', 'debug this test', 'large migration', or 'run a workflow' and the orchestrator routes to the right skill without the /hyperflow:* prefix. /hyperflow:workflow uses Claude Code dynamic workflows for big tasks and a portable Codex/OpenCode adapter where native workflows are unavailable; /hyperflow:spec asks the questions a senior engineer would; /hyperflow:scope decomposes into a batched task graph; /hyperflow:dispatch fans out persona-stitched workers under tiered review; /hyperflow:amplify rewrites a rough prompt into a high-quality one before you run it. 15 composable personas, 6 adaptive flow profiles, and persistent project memory compound across sessions. Works across Codex App/CLI, Claude Code, OpenCode, and Antigravity.

ai agency v4.26.1
View Plugin

Installation

This skill is included in the hyperflow plugin:

/plugin install hyperflow@claude-code-plugins-plus

Click to copy

Instructions

hyperflow-scope — decomposition phase (Antigravity single-agent)

Decompose, don't build. The only writes are to .hyperflow/. Follow the hyperflow doctrine.

Steps

  1. Research the affected surface (files to read/modify/create, conventions, test patterns). If the request is actually a design question, redirect to hyperflow-spec and stop.
  2. Produce a batch graph. Order batches topologically; each sub-task = one coherent change nameable in a single conventional-commit subject. Split any sub-task that touches >5 files, >500 LOC, spans 2+ subsystems, or would take a reviewer >10 min to grasp.
  3. Write .hyperflow/tasks/.md with: status table (progress, branch, commit cadence) → Goal → Why → Scope-at-a-glance table → Affected files (created/modified) → Execution plan (batch graph) → Batches (each sub-task with role, files, complexity, acceptance criteria, commit-message stub) → Verification plan.
  4. Print a one-line summary: Plan ready — .hyperflow/tasks/.md (N batches, M sub-tasks).
  5. Hand off: invoke the hyperflow-dispatch skill with the task slug.

Rules

  • No implementation code; no source edits.
  • Single-batch plans for multi-file work are an anti-pattern — decompose.
  • Always include a concrete verification plan.

Ready to use hyperflow?