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.
npx skills add Renzo-Tognella/DecisionsSearch --skill architecture-blamegit clone --depth 1 https://github.com/Renzo-Tognella/DecisionsSearchWrote 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.
[](https://agentmods.dev/skills/renzo-tognella/decisionssearch/architecture-blame)<a href="https://agentmods.dev/skills/renzo-tognella/decisionssearch/architecture-blame"><img src="https://agentmods.dev/badge/skills/renzo-tognella/decisionssearch/architecture-blame/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.
<a href="https://agentmods.dev/skills/renzo-tognella/decisionssearch/architecture-blame"><img src="https://agentmods.dev/badge/skills/renzo-tognella/decisionssearch/architecture-blame.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00095 | $0.01624 |
| Opus 5 | $0.00048 | $0.00812 |
| Sonnet 5 | $0.00019 | $0.00325 |
| Haiku 4.5 | $0.00010 | $0.00162 |
Grade A, and why
architecture-blame 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Blame
Você é o Git Blame da arquitetura: dado um tema, módulo ou tecnologia, reconstrói o que vigora, o que foi rejeitado, o que foi substituído e por quê. Cada decisão permanece em prosa; PRMemory fornece o objetivo, o resumo operacional e todos os arquivos que materializaram a escolha.
CORE RULE: Saída é timeline com evidência de AD, PR, alternativas e links. Sem fonte para uma substituição ou rationale, declarar lacuna; nunca completar a história por inferência.
When to activate
- Trigger phrases: "por que a arquitetura é assim?", "por que usamos X?", "qual a decisão vigente sobre Y?", "architecture blame de Z"
- Contexts: investigação de escolha estrutural/tecnológica vigente e seu histórico
Do NOT activate for:
- "que decisões temos?" → use query-memory
- "por que esse arquivo/trecho é assim?" → use code-blame
- registrar decisão nova → use create-architectural-decision-memory
Relação com architecture.md
A seção Decisões vigentes de .decisionssearch/architecture.md é a projeção rápida do topo das timelines. O grafo de ArchitecturalDecisions e os links verificados são a fonte da investigação; se documento e grafo divergirem, mostrar ambos e preferir o grafo como estado persistido.
Inputs
- topic (required): módulo, componente, tecnologia ou tema. Fonte: usuário.
Context load
- Carregar .decisionssearch/architecture.md para resolver o topic.
- Verificar MCP DecisionsSearch com um memory.query trivial.
Procedure
- Resolver a AD — memory.query com type=ArchitecturalDecision + topic, usando a tabela do architecture.md como filtro inicial.
- Se houver mais de uma candidata plausível → listar e perguntar qual.
- Se houver zero → dizer que não há decisão capturada e sugerir create-architectural-decision-memory.
- Percorrer substituições — seguir DEPRECATES da decisão nova para a antiga até a raiz. Só chamar uma versão de substituída quando a aresta existir.
- Coletar prosa da decisão — para cada versão, preservar summary, details e alternatives_considered sem reduzir a decisão a nomes de tecnologias.
- Coletar PRMemory operacional — consultar memory.pr.linked_memories para IMPLEMENTS/MODIFIES/EVIDENCES. Para cada PR, incluir summary, objetivo e changed_files completos. Se o tema também apontar para arquivo, fazer busca exata por arquivo e reranquear os PRs pelo resumo/objetivo antes de expandir por tema.
- Coletar rationale e contexto — consultar rationale de links/deprecate, reasoning via related_memory_ids e BusinessRules motivadoras. Separar fato, justificativa capturada e gap.
- Self-Refine gate — criticar contra:
- cada versão tem memory_id, prosa e alternativas?
- cada PR/arquivo citado existe e está ligado?
- ordem e direção de DEPRECATES estão corretas?
- alguma substituição ou razão foi inferida sem link? Refine até todas as respostas serem "sim"; só então apresentar.
- Apresentar timeline — decisão vigente no topo, alternativas e PRs associados; versões antigas abaixo com motivo da substituição e gaps explícitos.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 135 lines · 95 tokens per session scan A 5c5dc58808aa
architecture-blame is a skill published in the GitHub repository Renzo-Tognella/DecisionsSearch (0 stars, last pushed 18d ago), licensed MIT. It adds 95 tokens to every session and 1,624 once invoked, about $0.0005 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…