spec-design

spec-design is a command for coding agents from mrvladd-d/memobank. It costs 16 tokens per session (2,377 once invoked), scanned A, original, MIT.

A command that creates the project's shared software design foundation after requirements have been organized. It adapts the amount of design documentation to the size and complexity of the project.

In plain words
What is it for?
Use it after PRD decomposition to define the project's architecture, boundaries, contracts, states, testing approach, and other shared design areas.
Why use it?
It records important architecture decisions and unresolved blockers before feature-specific design or task planning begins.

Command

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/mrvladd-d/memobank/spec-design
Clone the repo
git clone --depth 1 https://github.com/mrvladd-d/memobank

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.

agentmods badge for spec-design

README.md
[![agentmods](https://agentmods.dev/badge/commands/mrvladd-d/memobank/spec-design.svg)](https://agentmods.dev/commands/mrvladd-d/memobank/spec-design)
Your own site
<a href="https://agentmods.dev/commands/mrvladd-d/memobank/spec-design"><img src="https://agentmods.dev/badge/commands/mrvladd-d/memobank/spec-design.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,377 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 $0.00016 $0.02377
Opus 5 $0.00008 $0.01189
Sonnet 5 $0.00003 $0.00475
Haiku 4.5 $0.00002 $0.00238

Measured 5d ago against content hash 7f599935e30a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-design 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 5d 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.

skills/_shared/references/commands/spec-design.md · 187 lines

How it starts

The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/spec-design - Global SDD backbone gate

The gate is mandatory by workflow, but adaptive by depth:

  • simple T0/T1 projects create a minimal backbone and mark irrelevant areas not_applicable;
  • projects with shared/T2/T3 concerns get staged architecture decisions and normal backbone specs;
  • unresolved key decisions are recorded as blockers and downstream commands must stop.

/spec-design does not create TASK records, implementation plans, or feature-local tech specs, and it does not replace /spec-improve.

0) Input and timing

Run after /prd.

Supported arguments:

  • no argument: inspect all current features and update the global backbone
  • --all: same as no argument; explicit for autonomous or batch flow

Required inputs:

  • .memory-bank/spec-index.md
  • .memory-bank/requirements.md
  • .memory-bank/epics/
  • .memory-bank/features/
  • existing relevant specs under .memory-bank/architecture/, .memory-bank/guides/, .memory-bank/domains/, .memory-bank/contracts/, .memory-bank/states/, .memory-bank/adrs/, .memory-bank/testing/, and .memory-bank/runbooks/

Never skip the command. For small independent T0/T1-only scope, write the minimal backbone status and mark non-applicable areas instead of expanding architecture.

1) Backbone status gate

Update .memory-bank/spec-index.md with a clear global backbone status:

  • complete: shared/global decisions are recorded and no blocker remains
  • minimal: project is simple/T0-T1 oriented; unnecessary areas are explicitly not_applicable
  • blocked: key architecture decisions are unresolved

If status is blocked, stop downstream work. Record:

  • unresolved decision
  • affected features/requirements
  • why a conservative assumption would be unsafe
  • next question or owner needed

2) Spec-index content contract

.memory-bank/spec-index.md is an index and route map, not an authoritative design spec.

Read the full file on GitHub · 187 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. 5d ago First seen · 187 lines · 16 tokens per session scan A 7f599935e30a

Subscribe to this mod's changes

spec-design is a command published in the GitHub repository mrvladd-d/memobank (55 stars, last pushed 3mo ago), licensed MIT. It adds 16 tokens to every session and 2,377 once invoked, about $0.0001 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 2026-08-30.