A workflow that turns a vague feature idea into a structured proposal with smaller work items. It uses a product manager agent, asks for human approval, and then passes the approved proposal to the next planning stage.

Use it to shape a new feature or opportunity into an approved pitch and a set of development epics.

It creates a shared, reviewable plan before development begins, so unclear ideas can be corrected early.

shape — Skill for Claude Code by NVZver

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add NVZver/claude-marketplace --skill shape

Clone the repo

git clone --depth 1 https://github.com/NVZver/claude-marketplace

Made for: Claude Code.

Or install manager, the plugin that ships this one along with the rest of its 5 skills, 2 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/nvzver/claude-marketplace/shape.svg)](https://agentmods.dev/skills/nvzver/claude-marketplace/shape)

Your own site

<a href="https://agentmods.dev/skills/nvzver/claude-marketplace/shape"><img src="https://agentmods.dev/badge/skills/nvzver/claude-marketplace/shape.svg" alt="Measured on agentmods" height="20"></a>

Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,416 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00097	$0.01416
Opus 5	$0.00048	$0.00708
Sonnet 5	$0.00019	$0.00283
Haiku 4.5	$0.00010	$0.00142

Measured 8d ago against content hash 1ee9530d69f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

shape scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

manager/skills/shape/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Trace. On load, print first: =============== [manager/skills/shape/SKILL.md] [manager] ===============

Start Feature

Orchestrator skill. Accepts a vague idea, dispatches the product-manager agent for shaping, runs the agent's returned human gates via an interactive confirmation gate (AskUserQuestion in Claude Code), then hands off to manager:decompose for epic decomposition. Does not contain shaping logic or decomposition logic — those live in the agents.

Goal

Go from a vague idea to a human-approved pitch with epics ready for the LSA build cycle — without the user manually shaping the pitch or invoking agents directly.

Input

Problem or opportunity description (argument to the skill, or interactive prompt if no argument given).
specs_root from .lsa.yaml at repo root (defaults per ../../../lsa/knowledge/conventions.md §".lsa.yaml defaults"). Used to resolve ${specs_root}/... paths below.

Steps

Accept input. Read the argument. If no argument provided, prompt the user for a problem or opportunity description. Observable result: description captured.
Dispatch product-manager agent. Invoke the product-manager agent by dispatching it as a sub-agent (Agent in Claude Code) with the problem description. Wait for the agent to complete. Observable result: agent returns the full draft pitch content + proposed slug + an ordered pending-gates list (role confirmation, shaping forks with recommended defaults, final approve/reshape/reject) per ../../agents/product-manager.md Step 5. Nothing is on disk.
Deliver the pitch, then run the returned gates. The agent's payload is invisible to the user — this skill re-renders it. First deliver the full pitch content per the core/output Rule 7 Delivery test: as the turn-final message (no tool calls after it in that turn), or carried inside the gates below (option preview). Then present each pending gate via an interactive confirmation gate (AskUserQuestion in Claude Code) (Rule 5 Self-contained gates), in the agent's order: role confirmation first, then each shaping fork (offering the agent's recommended default), then the final approve / reshape / reject.
- Approve: write the pitch to ${specs_root}/pitches/<slug>.md with Status: approved and the gate decisions (confirmed role, fork choices) in the metadata header; quote the written file inline — show → approve → write per Rule 7 Authorization boundary.
- Reshape: re-dispatch the agent with the user's feedback (a continuation message — SendMessage in Claude Code — or a new dispatch if the agent has exited), then deliver + gate the fresh payload again.
- Reject: write nothing — no file exists. State the rationale in the conversation and exit cleanly — no downstream work.

Read the full file on GitHub · 69 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

8d ago First seen · 69 lines · 97 tokens per session scan A 1ee9530d69f0

Subscribe to this mod's changes

shape is a skill published in the GitHub repository NVZver/claude-marketplace (1 stars, last pushed 14d ago), licensed MIT. It adds 97 tokens to every session and 1,416 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude Code Planning Project management ai-agents claude-code-marketplace claude-code-plugin prompt-engineering spec-driven-development

traction-eos

Implement the Entrepreneurial Operating System (EOS) to align vision and execution across a company. Use when the user mentions "EOS", "Entrepreneurial Operating System", "V/TO", "quarterly rocks", "Level 10 meetings", "accountability chart", "IDS process", "my company feels chaotic", "we keep having the same…

wondelai/skills · 147 tokens

predictable-revenue

Build a scalable outbound B2B sales machine with specialized roles (SDR, AE, CSM). Use when the user mentions "outbound sales", "Cold Calling 2.0", "cold email sequences", "sales pipeline", "SDR process", "sales development", "build an outbound sales team", or "fill my pipeline". Also trigger when setting up a B2B…

wondelai/skills · 152 tokens

team-topologies

Organize business and technology teams for fast flow using Skelton & Pais's "Team Topologies". Use when the user mentions "team topologies", "Conway's law", "platform team", "stream-aligned team", "team boundaries", "cognitive load", "how should we split teams", "who owns this service", "team dependencies", or…

wondelai/skills · 155 tokens

glab

Expert guidance for using the GitLab CLI (glab) to manage GitLab issues, merge requests, CI/CD pipelines, repositories, and other GitLab operations from the command line. Use this skill when the user needs to interact with GitLab resources or perform GitLab workflows.

NikiforovAll/claude-code-rules · 59 tokens

foreman

The one entrance to Foreman — say what you want in plain language and this routes it. Covers the six things Foreman does to a project: add work, show status, correct work, check the roadmap, pick work, or reconcile and pick. It owns no flow of its own; each intent is handed to the skill that already implements it, so…

V-Songbird/foreman · 0 tokens

spec-flow

Use when planning, executing, checkpointing, finishing, or inspecting lightweight spec-driven work. Runs one task at a time using .spec/ markdown files and the bundled specctl helper. NOT for broad product discovery beyond a short requirement interview. NOT for generic implementation planning that does not read or…

alexei-led/cc-thingz · 71 tokens