shape-spec

A planning command that gathers project context and shapes a significant coding task into a lightweight plan through questions and suggested options.

In plain words
What is it for?
Use it in plan mode to clarify a feature or change, identify constraints, and outline the work.
Why use it?
It helps turn an unclear or broad request into an agreed scope before implementation begins.

Command for Claude Code

Part of the smartspender plugin — 13 skills, 19 commands shipped together

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.

agentmods
npx agentmods add commands/peerjakobsen/smartspender/shape-spec
Clone the repo
git clone --depth 1 https://github.com/peerjakobsen/smartspender

Made for: Claude Code.

Or install smartspender, the plugin that ships this one along with the rest of its 13 skills, 19 commands.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,525 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01525
Opus 5 $0.00000 $0.00763
Sonnet 5 $0.00000 $0.00305
Haiku 4.5 $0.00000 $0.00153

Measured 3d ago against content hash fbe80764a0b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

shape-spec 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 3d 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.

.claude/commands/agent-os/shape-spec.md · 268 lines

How it starts

The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Shape Spec

Gather context and structure planning for significant work. Run this command while in plan mode.

Important Guidelines

  • Always use AskUserQuestion tool when asking the user anything
  • Offer suggestions — Present options the user can confirm, adjust, or correct
  • Keep it lightweight — This is shaping, not exhaustive documentation

Prerequisites

This command must be run in plan mode.

Before proceeding, check if you are currently in plan mode.

If NOT in plan mode, stop immediately and tell the user:

Shape-spec must be run in plan mode. Please enter plan mode first, then run /shape-spec again.

Do not proceed with any steps below until confirmed to be in plan mode.

Process

Step 1: Clarify What We're Building

Use AskUserQuestion to understand the scope:

What are we building? Please describe the feature or change.

(Be as specific as you like — I'll ask follow-up questions if needed)

Based on their response, ask 1-2 clarifying questions if the scope is unclear. Examples:

  • "Is this a new feature or a change to existing functionality?"
  • "What's the expected outcome when this is done?"
  • "Are there any constraints or requirements I should know about?"

Step 2: Gather Visuals

Use AskUserQuestion:

Do you have any visuals to reference?

- Mockups or wireframes
- Screenshots of similar features
- Examples from other apps

(Paste images, share file paths, or say "none")

If visuals are provided, note them for inclusion in the spec folder.

Step 3: Identify Reference Implementations

Use AskUserQuestion:

Is there similar code in this codebase I should reference?

Examples:
- "The comments feature is similar to what we're building"
- "Look at how src/features/notifications/ handles real-time updates"
- "No existing references"

(Point me to files, folders, or features to study)

If references are provided, read and analyze them to inform the plan.

Step 4: Check Product Context

Read the full file on GitHub · 268 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.

  1. 3d ago First seen · 268 lines · 0 tokens per session scan A fbe80764a0b3

Subscribe to this mod's changes

shape-spec is a command published in the GitHub repository peerjakobsen/smartspender (5 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,525 tokens. 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.