hyperflow-plan
Hyperflow planning phase. Use when a request needs shaping before code — a rough prompt to sharpen, an ambiguous idea to design, or a clear-enough task to decompose. Verbs like plan, design, brainstorm, explore, "should we", "what's the best way to", scope, decompose, "plan out", "break down", "enhance this prompt". Thinking, not building. Writes an optional spec to .hyperflow/specs/<slug>.md and a task file to .hyperflow/tasks/<slug>.md, then hands off to hyperflow-dispatch.
Allowed Tools
No tools specified
Provided by Plugin
hyperflow
Point it at a GitHub issue and get back a reviewed pull request. Hyperflow turns one AI coding session into a structured engineering pipeline: plan sharpens and decomposes the work, dispatch fans out parallel workers, and a domain specialist reviews every step — nothing ships unreviewed. 18 skills, 22 specialist reviewer and investigator agents, adaptive depth so a 5-line fix never triggers a deep run, and persistent per-project memory that lives in your repo and never leaves it. Runs on whatever model your session already uses — zero config, no API keys, no daemon. Works across Claude Code, Codex App/CLI, OpenCode, Grok, Antigravity, and Cursor.
Installation
This skill is included in the hyperflow plugin:
/plugin install hyperflow@claude-code-plugins-plusClick to copy
Instructions
hyperflow-plan — planning phase (Antigravity single-agent)
Thinking, not building. The only writes are to .hyperflow/. Each phase skips itself when the request doesn't need it. Follow the hyperflow doctrine (autonomy, file-first, AskUserQuestion gates).
Steps
- Amplify (skippable). If the prompt is rough, rewrite it into its strongest form — role · task · context · constraints · output spec. Skip when it's already specific. Never inflate a one-line ask into a spec.
- Research first. Read the relevant code,
AGENTS.md, and.hyperflow/memory/*. Map the affected surface yourself — do not ask what the code answers. - Design (skippable). For an open-ended request: ask ≥2 clarifying questions (what/which/where only), propose 2–3 approaches, then design section-by-section into
.hyperflow/specs/with approval per section. A clear request bounces straight to decomposition. When a system, UI, motion, or mobile surface is in scope, ground the design in the matching standards (architecture decomposition + a diagram, the design system, the Motion language, the mobile platform/device matrix)..md - Decompose. Produce a topologically-ordered batch graph; each sub-task = one conventional-commit-sized change. Split any sub-task touching >5 files, >500 LOC, 2+ subsystems, or >10-min review. Write
.hyperflow/tasks/: status table → Goal → Why → Scope-at-a-glance → Affected files → Execution plan → Batches (role, files, complexity, acceptance criteria, commit stub) → Verification plan..md - Print
Plan ready — .hyperflow/tasks/..md (N batches, M sub-tasks) - Hand off: invoke the
hyperflow-dispatchskill with the task slug — or, in two-session mode, write a committed handoff package and stop.
Rules
- No implementation code; no source edits.
- Floor of 2 clarifying questions on the design path; 0–3 on the bounce (decompose-only) path.
- Single-batch plans for multi-file work are an anti-pattern — decompose.
- Always include a concrete verification plan.