What is spec-kit-architecture?

An architecture-planning guide for documenting software components, boundaries, contracts, data ownership, processing style, security, and observability.

Use it to define or review the architecture document and identify contracts, responsibilities, data ownership, consistency needs, and related open questions.

It turns functional requirements into a coherent technical structure and records important decisions or missing information instead of filling gaps with guesses.

How lksnext-ai-lab/spec-kit-template configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to lksnext-ai-lab/spec-kit-template. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/lksnext-ai-lab/spec-kit-template/main/.github/skills/spec-kit-architecture/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/lksnext-ai-lab/spec-kit-template

Made for: Claude Code.

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/lksnext-ai-lab/spec-kit-template/spec-kit-architecture/github.svg)](https://agentmods.dev/skills/lksnext-ai-lab/spec-kit-template/spec-kit-architecture)

Your own site

<a href="https://agentmods.dev/skills/lksnext-ai-lab/spec-kit-template/spec-kit-architecture"><img src="https://agentmods.dev/badge/skills/lksnext-ai-lab/spec-kit-template/spec-kit-architecture/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/lksnext-ai-lab/spec-kit-template/spec-kit-architecture"><img src="https://agentmods.dev/badge/skills/lksnext-ai-lab/spec-kit-template/spec-kit-architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,297 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	$0.00056	$0.01297
Opus 5.5	$0.00022	$0.00519
Sonnet 5.5	$0.00011	$0.00259
Haiku 4.5	$0.00006	$0.00130

Measured 2mo ago against content hash 3df1729d71a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

spec-kit-architecture 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 2mo 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.

.github/skills/spec-kit-architecture/SKILL.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Architecture (spec-kit)

Objetivo

Dejar docs/spec/40-arquitectura.md en un estado ejecutable y coherente con FR/NFR, minimizando suposiciones:

componentes y responsabilidades (límites claros),
contratos entre componentes e integraciones externas,
criterios sync/async + consistencia/idempotencia cuando aplique,
ownership de datos,
seguridad y observabilidad mínima (MVP),
decisiones y gaps (ADR/OPENQ).

Archivos que se pueden modificar

Primario: docs/spec/40-arquitectura.md
Si aplica (solo cuando haga falta):
- docs/spec/adr/ADR-*.md (decisiones)
- docs/spec/95-open-questions.md (gaps críticos)
- docs/spec/96-todos.md (acciones/pendientes no bloqueantes)

No tocar otros ficheros de docs/spec/** salvo petición explícita del usuario.

Inputs recomendados

docs/spec/10-requisitos-funcionales.md
docs/spec/11-requisitos-tecnicos-nfr.md
docs/spec/50-modelo-datos.md (si hay datos)
Evidence Packs relevantes: docs/spec/_inputs/evidence/
ADRs existentes: docs/spec/adr/

Reglas duras

No inventar

Si algo condiciona la arquitectura y no está claro → OPENQ (no “rellenar”).

Arquitectura = to-be, pero basada en drivers

En la arquitectura, cada bloque importante debe referenciar drivers (FR/NFR/ADR/EP).
Si una decisión no está cerrada: marcarla como DECISION PENDIENTE y abrir ADR/OPENQ.

Cada trade-off relevante → ADR Crear ADR cuando se elige entre opciones con impacto (p.ej. sync vs async, modelo de permisos, estrategia de idempotencia, etc.).
Diff-friendly

Cambios acotados y estructurados; evitar reescrituras masivas.

Workflow (determinista)

1) Drivers y supuestos (1 pantalla)

En 40-arquitectura.md, abrir con:

Drivers FR/NFR (5–12 bullets)
Restricciones (técnicas/operativas/legales) (3–8 bullets)
Supuestos explícitos (si no están en spec → OPENQ)

2) Snapshot de arquitectura (alto nivel)

Lista de componentes (máx. 12 en MVP; si hay más, agrupar por “dominio/capacidad”).
Diagrama ASCII breve (opcional, pero recomendado).
Tabla de límites:
- Componente | Responsabilidad | Interfaces | Datos que posee | Dependencias

Read the full file on GitHub · 125 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.

2mo ago First seen · 125 lines · 56 tokens per session scan A 3df1729d71a6

Subscribe to this mod's changes

spec-kit-architecture is a skill published in the GitHub repository lksnext-ai-lab/spec-kit-template (5 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 56 tokens to every session and 1,297 once invoked, about $0.0002 per session on Opus 5.5. 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.

Planning

spec-kit-architecture next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
spec-kit-architecturelksnext-ai-lab/spec-kit-template	Skill	5	8mo ago	Apache-2.0	A	56	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code

spec-kit-template: Skill for Claude Code