A guide for recording important technical choices in an Architecture Decision Record, or ADR. An ADR documents the context, rejected alternatives, consequences, and reversal path for a decision.

Use it when choosing between plausible designs such as libraries, storage, caching, authentication, or buying versus building, and when replacing an existing decision.

It preserves why a choice was made so future developers can understand it without repeating the original investigation.

How darcivieira/kanbanize-sdk configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to darcivieira/kanbanize-sdk. 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/darcivieira/kanbanize-sdk/main/.claude/skills/spec-adr/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/darcivieira/kanbanize-sdk

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/darcivieira/kanbanize-sdk/spec-adr/github.svg)](https://agentmods.dev/skills/darcivieira/kanbanize-sdk/spec-adr)

Your own site

<a href="https://agentmods.dev/skills/darcivieira/kanbanize-sdk/spec-adr"><img src="https://agentmods.dev/badge/skills/darcivieira/kanbanize-sdk/spec-adr/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/darcivieira/kanbanize-sdk/spec-adr"><img src="https://agentmods.dev/badge/skills/darcivieira/kanbanize-sdk/spec-adr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 608 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	$0.00098	$0.00608
Opus 5.5	$0.00039	$0.00243
Sonnet 5.5	$0.00020	$0.00122
Haiku 4.5	$0.00010	$0.00061

Measured 2mo ago against content hash b467322032d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

spec-adr 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.

.claude/skills/spec-adr/SKILL.md · 46 lines

What it actually says

spec-adr

Antes de tudo: isto é mesmo um ADR?

Situação	Onde vai
Havia alternativa plausível e ela foi descartada	ADR
Só uma forma razoável de fazer	`governanca/02-convencoes.md`
Regra que nunca pode ser violada	`governanca/01-constituicao.md`
Como o sistema é montado hoje	`arquitetura/VISAO_TECNICA.md`

Se a tabela "Alternativas descartadas" ficaria vazia, não é ADR. Não crie.

Criar

Próximo número livre em specs/arquitetura/adr/, 4 dígitos, nunca reaproveitado.
Arquivo NNNN-slug-curto.md a partir de specs/_templates/ADR.md.
Preencha:
- Contexto: restrições reais no momento, incluindo o que era desconhecido. Isto é o que dá valor ao ADR daqui a um ano.
- Alternativas descartadas: com o motivo real, não o motivo elegante.
- Consequências: ganhos, custos, e o que fica mais difícil depois.
- Como reverter: custo e caminho. Se for irreversível, diga.
- Sinais de envelhecimento: o que observar que indicaria hora de um sucessor.
Status aceito só quando o humano confirmar. Antes disso, proposto.
Atualize o índice em specs/arquitetura/adr/README.md.

Substituir

Nunca edite um ADR aceito. O registro do que se pensava é o produto.

Crie o sucessor com substitui: NNNN e explique no contexto o que mudou desde então.
No antigo, altere apenas status: substituído e substituido-por: MMMM.
Atualize o índice.

Regra de escrita

Contexto e alternativas em fatos e restrições, não em justificativa retrospectiva. "Escolhemos X porque é melhor" não é ADR. "Escolhemos X porque Y exigia Z que não tínhamos até , ao custo de W" é.

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 · 46 lines · 98 tokens per session scan A b467322032d1

Subscribe to this mod's changes

spec-adr is a skill published in the GitHub repository darcivieira/kanbanize-sdk (2 stars, last pushed 2mo ago), licensed MIT. It adds 98 tokens to every session and 608 once invoked, about $0.0004 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 2026-09-04.

Planning

spec-adr next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
spec-adrdarcivieira/kanbanize-sdk	Skill	2	2mo ago	MIT	A	98	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

kanbanize-sdk: Skill for Claude Code