plan
Use when a request needs shaping before any code is written — a rough or vague prompt to sharpen, an ambiguous idea to design, or a clear-enough task to decompose. One chain-starter that amplifies the prompt, designs the approach, and decomposes it into a batched task file, skipping whichever phases the request doesn't need, then STOPS at a build-location gate (build here, hand off to another session, or just keep the plan). Plan never implements. Trigger with /hyperflow:plan, "design this", "plan this", "decompose this", "how should we", "what's the best way to", "break this down", "enhance
npx skills add jeremylongshore/claude-code-plugins-plus-skills --skill plan --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
The skill acts as a planning chain that amplifies a vague or structured prompt, designs an approach, and decomposes the work into a batched task file, then stops at a build-location gate. It does not implement code or silently dispatch tasks.
How it works
- It runs in three phases (amplify, design, decompose) and writes artefacts to disk (e.g.,
.hyperflow/specs/,.hyperflow/tasks/, etc.). - It always ends by asking where to build: this session, another session, or stop, at Step 12 (build-location gate).
- It uses a multi-step flow with gates and reviews: Step 1 (Triage), Step 2 (Amplify), Step 3 (Context), Step 4 (Multi-dim analysis), Step 5 (Clarify), Step 6 (Synthesis + approaches), Step 7 (Design sections), Step 8 (Spec finalize), Step 9 (Decompose), Step 10 (Write task file), Step 11 (Memory), Step 12 (Build-location gate).
- It relies on tools like Writer, Reviewer, Writer(architect/designer/mobile roles), Planner, and Analyst inside a Claude Code context.
When to use it
Trigger phrases include "/hyperflow:plan", "design this", "plan this", "decompose this", "how should we", "what's the best way to", "break this down", and "enhance this prompt". Use when a request needs shaping before any code is written or when a task should be decomposed into a batched plan.
What it can touch
It writes to artifacts in .hyperflow/specs/, .hyperflow/tasks/, .hyperflow/features/, .hyperflow/memory/, and (in handoff mode) the .hyperflow-handoff/ package. It uses tools including Write, Read, Edit, and various Bash and Glob operations as part of the workflow. It requires Claude Code compatibility.
Caveats
- Plan never implements code; it stops at the build-location gate and does not silently dispatch.
- It performs maximum thinking depth and may produce build-ready briefs or task files intended for subsequent sessions.
- If a non-trivial sub-task is identified, it will generate a build-ready brief (
briefs=auto). - Failure recovery rules exist for triage and planning errors and should be consulted if issues arise.
# Plan One chain-starter that folds three phases — **amplify** (sharpen the prompt), **design** (brainstorm and spec the approach), **decompose** (write the batched task file) — into a single flow, then **stops at a build-location gate** (Step 12). Each phase skips itself when the request doesn't need it: a clear task bounces straight to decomposition; an already-structured prompt skips amplify. *
What does the plan skill do?
Use when a request needs shaping before any code is written — a rough or vague prompt to sharpen, an ambiguous idea to design, or a clear-enough task to decompose. One chain-starter that amplifies the prompt, designs the approach, and decomposes it into a batched task file, skipping whichever phases the request doesn't need, then STOPS at a build-location gate (build here, hand off to another session, or just keep the plan). Plan never implements. Trigger with /hyperflow:plan, "design this", "plan this", "decompose this", "how should we", "what's the best way to", "break this down", "enhance
How do I install it?
Run `npx skills add jeremylongshore/claude-code-plugins-plus-skills --skill plan --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From jeremylongshore/claude-code-plugins-plus-skills, a repository with 2,596 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.