spec

A command that turns a complex feature request into a short written specification before coding starts. It clarifies the goal, scope, affected parts of the code, and how the work will be checked.

In plain words
What is it for?
Use it to plan features involving several files, user-facing changes, or outside-system integrations. It asks focused questions and records the agreed approach and boundaries.
Why use it?
It prevents coding from beginning with unclear requirements or hidden architectural decisions. It also keeps a feature small enough to deliver as one complete piece.

Command for Claude Code

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/heiko-braun/draft/spec
Clone the repo
git clone --depth 1 https://github.com/heiko-braun/draft

Made for: Claude Code.

Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 736 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 $0.00030 $0.00736
Opus 5 $0.00015 $0.00368
Sonnet 5 $0.00006 $0.00147
Haiku 4.5 $0.00003 $0.00074

Measured 2d ago against content hash 645a01bb1fe8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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/spec.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Specification Generator

You help users clarify requirements and create lightweight specifications before implementation begins.

Each spec represents a single vertical slice — a small, complete unit of work delivered in one pass. Specs are not partial deliveries or large application blueprints.

When to Activate

Automatically engage when the user requests a feature that involves:

  • Multiple files or components
  • Architectural decisions
  • User-facing changes
  • Integration with external systems

Do NOT activate for:

  • Simple bug fixes with obvious solutions
  • Single-line changes
  • Documentation updates
  • Dependency updates

Workflow

Phase 1: Clarify (3-5 questions max)

Ask questions ONE AT A TIME. Do not batch multiple questions. Wait for each answer before proceeding.

Suggested questions (adapt to context):

  1. What problem does this solve? Who benefits?
  2. What's the simplest version that would be useful?
  3. Any constraints? (performance, compatibility, existing patterns to follow)
  4. What should explicitly be OUT of scope?
  5. Modularity: What existing modules or interfaces will this touch? Can the change be encapsulated behind a new or existing boundary, or does it require changes across many modules?

Use the project's existing patterns and tech stack to inform your questions. Reference specific files when relevant.

Phase 1.5: Scope Check

Before drafting, assess whether the feature is small enough for a single spec:

  • More than 5 acceptance criteria? Likely too big — suggest splitting into multiple specs.
  • Touches many unrelated modules? The blast radius is too wide — look for a narrower interface or split by module boundary.
  • Cannot be described in 2-3 sentences of approach? The feature may need decomposition.

If the scope is too large, propose how to split it into multiple independent specs, each deliverable on its own.

Phase 2: Draft Spec

Write a brief spec to /specs/{feature-name}.md using the template in /specs/TEMPLATE.md.

Read the full file on GitHub · 83 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. 2d ago First seen · 83 lines · 30 tokens per session scan A 645a01bb1fe8

Subscribe to this mod's changes

spec is a command published in the GitHub repository heiko-braun/draft (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 30 tokens to every session and 736 once invoked, about $0.0002 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.